docs(registry): 14 novos packs + 3 refreshes (Phase 2 cadence)#10
Merged
Conversation
Phase 2 cadence — repos discovered through social-media browsing,
analyzed and cataloged using the standard one-pager template.
Novos packs:
- agent-exchange (marketplace for AI agents, MIT, experimental)
- agent-skills-eval (A/B test runner for skills, MIT)
- ascii-draw (GTK4 ASCII drawing, GPL-3.0)
- claude-code-harness (Plan-Work-Review-Release, MIT)
- crawlee (web scraping for LLM/RAG, Apache-2.0)
- cryptpad (E2E-encrypted office suite, AGPL-3.0)
- googleworkspace-cli (official Google CLI + 100+ SKILL.md, Apache-2.0)
- isomiddleearth (Next.js 16 reference impl, license unstated)
- jeweledtech-agentic-framework (multi-dept biz orchestration, MIT)
- locally-uncensored (local-first multi-modal desktop, AGPL-3.0)
- mirothinker (deep-research agent on Qwen + MCP, Apache-2.0)
- openhuman (personal AI agent, 118+ integrations, GPL-3.0)
- quran-database (MySQL Quran dataset, public domain text)
- understand-anything (codebase-as-knowledge-graph plugin, MIT)
Refreshed (already in registry):
- fincept-terminal (stars 18.3k -> 20.5k)
- auto-research-claw (stars 11.8k -> 12k)
- ruflo (stars 34.1k -> 47.7k, v3.6.10 -> v3.6.30)
INDEX + tag wiring:
- INDEX.md: 14 new rows, 3 refreshes, "Last index update" bumped
- tags/{ai,agents-marketplace,data-engineering,design,ecosystem,
learning,productivity,research,security}.md: cross-links added
See session-log/2026-05-09-registry-additions.md for full rationale,
including: MiroThinker vs MiroShark distinction, googleworkspace-cli
as agents-marketplace tag rationale, AGPL flagging discipline.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📝 WalkthroughWalkthroughThis PR expands the registry with 14 new tool packs and refreshes 3 existing entries, adding comprehensive documentation pages, updating the main index, cross-referencing across 9 subject-area tags, and recording the work in a session log. ChangesRegistry Additions — 14 New Packs & 3 Metadata Refreshes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
🧹 Nitpick comments (1)
docs/registry/packs/mirothinker.md (1)
11-12: ⚡ Quick winPrefer evidence-neutral wording over “State-of-the-art.”
This superlative is time-sensitive and subjective. Consider replacing with benchmark-grounded phrasing (e.g., “reports strong performance on multiple research benchmarks”).
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/registry/packs/mirothinker.md` around lines 11 - 12, The phrase "State-of-the-art on multiple research benchmarks." is subjective and time-sensitive; replace it with an evidence-neutral statement such as "reports strong performance on multiple research benchmarks" and, where possible, add specific benchmark names or citations to support the claim (edit the sentence containing "State-of-the-art on multiple research benchmarks" in the mirothinker pack description).
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/registry/packs/cryptpad.md`:
- Line 38: Replace the inline code snippet `cryptpad.fr` with a clickable HTTPS
link so readers can open it directly; specifically update the sentence
containing "Or use the public hosted instance at `cryptpad.fr`" to use a
markdown link like "https://cryptpad.fr" (displaying either the full URL or
"cryptpad.fr") so it renders as a clickable HTTPS link.
In `@docs/registry/packs/isomiddleearth.md`:
- Around line 4-7: Update the top-level metadata so the Status explicitly
encodes the restriction while the License still notes “check upstream”: replace
the current "Status: active (553 stars)" entry with a clear restriction like
"Status: reference-only until upstream license is explicit" (you can keep the
star count in parentheses if desired) and keep the "License: check upstream (not
explicitly stated)" line unchanged; edit the Status field in this document
(isomiddleearth.md) to make the adoption restriction explicit.
In `@docs/registry/packs/quran-database.md`:
- Around line 51-53: Update the three bullet points that currently assert "Quran
text itself is in the public domain", flag the repo license as unclear, and warn
about translations so they avoid absolute legal language: change the first
bullet to say the canonical Arabic text is often treated as public-domain in
many jurisdictions but recommend users verify local law and provenance; modify
the second bullet (currently saying "Software license not explicitly stated") to
instruct readers to check the repository's LICENSE or contact maintainers before
redistributing schema/scripts commercially; and adjust the third bullet to
explicitly state that translation editions may have separate copyrights and must
be checked per-edition before bundling. Ensure the new wording is
jurisdiction-dependent and recommends concrete verification steps.
In `@docs/registry/packs/understand-anything.md`:
- Around line 32-34: Replace the platform-specific shell command "open
https://github.com/lum1104/understand-anything" with a cross-platform plain URL
or a neutral prompt (e.g., "Visit:
https://github.com/lum1104/understand-anything") in the
docs/registry/packs/understand-anything.md file so Linux/Windows users aren't
blocked by the macOS-only open command; update the single-line code block
containing that URL accordingly.
In `@docs/registry/tags/learning.md`:
- Line 21: The registry entry for `quran-database` currently asserts "public
domain"; change that phrase to a neutral, non-definitive note such as "license
pending verification" or "license status under review" so it doesn't assert
final license status; update the table cell text for the `quran-database` row to
reflect neutral wording and, if desired, add a brief parenthetical like
"(upstream license verification required)" to make the uncertainty explicit.
In `@session-log/2026-05-09-registry-additions.md`:
- Line 61: The heading "AGPL-3.0 packs flagged consistently" is misleading
because the list includes GPL-3.0 and AGPL+commercial entries (e.g., cryptpad,
locally-uncensored, openhuman, fincept-terminal); change the heading to
"copyleft-licensed packs flagged consistently" or split into two subheadings
("AGPL-licensed packs" and "GPL-licensed packs") and move each pack (cryptpad,
locally-uncensored, openhuman, fincept-terminal) under the correct subheading so
the license grouping matches the listed pack licenses.
- Line 27: The table row for `quran-database` currently states "public domain"
but the PR marks license verification as pending; update the entry for
`quran-database` (the table row containing the symbol `quran-database`) to a
provisional phrasing such as "provisional — license verification pending" or
"pending verification (provisional)" so the session log matches the PR summary.
---
Nitpick comments:
In `@docs/registry/packs/mirothinker.md`:
- Around line 11-12: The phrase "State-of-the-art on multiple research
benchmarks." is subjective and time-sensitive; replace it with an
evidence-neutral statement such as "reports strong performance on multiple
research benchmarks" and, where possible, add specific benchmark names or
citations to support the claim (edit the sentence containing "State-of-the-art
on multiple research benchmarks" in the mirothinker pack description).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 16e8c7c4-2c2e-4231-b047-201ab4ed7d52
📒 Files selected for processing (29)
docs/registry/INDEX.mddocs/registry/packs/agent-exchange.mddocs/registry/packs/agent-skills-eval.mddocs/registry/packs/ascii-draw.mddocs/registry/packs/auto-research-claw.mddocs/registry/packs/claude-code-harness.mddocs/registry/packs/crawlee.mddocs/registry/packs/cryptpad.mddocs/registry/packs/fincept-terminal.mddocs/registry/packs/googleworkspace-cli.mddocs/registry/packs/isomiddleearth.mddocs/registry/packs/jeweledtech-agentic-framework.mddocs/registry/packs/locally-uncensored.mddocs/registry/packs/mirothinker.mddocs/registry/packs/openhuman.mddocs/registry/packs/quran-database.mddocs/registry/packs/ruflo.mddocs/registry/packs/understand-anything.mddocs/registry/tags/agents-marketplace.mddocs/registry/tags/ai.mddocs/registry/tags/data-engineering.mddocs/registry/tags/design.mddocs/registry/tags/ecosystem.mddocs/registry/tags/learning.mddocs/registry/tags/productivity.mddocs/registry/tags/research.mddocs/registry/tags/security.mdsession-log/2026-05-09-registry-additions.mdsession-log/INDEX.md
Domínios que respondem com 999 (LinkedIn), 403 (Perestroika), ou timeout (Lume UFRGS) consistentemente — não são bugs de link, são anti-bot policies de hosts grandes que bloqueiam crawlers genéricos. URLs continuam válidas pra navegação humana. Sem exclusions o CI falhava em PRs que nem tocavam nesses arquivos (caso da PR #10). Também adicionado --accept 200..=299,403,429 pra cobrir respostas defensivas de outros sites no futuro sem nova edição. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- cryptpad.md: cryptpad.fr inline -> link clicavel - isomiddleearth.md: Status active -> reference-only ate license explicita - quran-database.md: linguagem absoluta sobre public domain -> jurisdiction-dependent - understand-anything.md: open URL (macOS-only) -> Visit URL (cross-platform) - tags/learning.md: row do quran sem assertiva de public domain - session-log: alinhado com PR (license pending) + heading copyleft no lugar de AGPL-only Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/workflows/ci.yml:
- Around line 62-70: The workflow currently passes --accept '200..=299,403,429'
in the args which globally treats 403/429 as successful; remove that global
--accept for 403/429 and instead add one or both mitigations: use retry/backoff
flags (e.g., add --max-retries and --retry-wait-time to the args) to retry
transient 429/403 responses, and/or stop accepting those codes and add
--exclude-path '.lycheeignore' to maintain a list of known anti-bot/problematic
URLs; if you must keep accepting 403/429, add an inline comment documenting the
risk and consider periodic manual link audits.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 1d492d79-a2eb-459d-b951-ff7146368c0e
📒 Files selected for processing (7)
.github/workflows/ci.ymldocs/registry/packs/cryptpad.mddocs/registry/packs/isomiddleearth.mddocs/registry/packs/quran-database.mddocs/registry/packs/understand-anything.mddocs/registry/tags/learning.mdsession-log/2026-05-09-registry-additions.md
✅ Files skipped from review due to trivial changes (5)
- docs/registry/tags/learning.md
- docs/registry/packs/isomiddleearth.md
- docs/registry/packs/understand-anything.md
- docs/registry/packs/quran-database.md
- docs/registry/packs/cryptpad.md
Aceitar 403/429 globalmente esconde links genuinamente quebrados. As exclusions especificas (linkedin/lume/perestroika) ja cobrem os hosts problematicos conhecidos. Mantemos retry com backoff pra rate-limits transientes mas sem deixar passar quebras reais. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
docs/registry/packs/seguindo o template padrão de uma páginafincept-terminal,auto-research-claw,ruflo) — bumped Last reviewed + version/star numberssession-log/2026-05-09-registry-additions.mdOs 14 novos packs
agent-exchangeagent-skills-evalascii-drawclaude-code-harnesscrawleecryptpadgoogleworkspace-cli⭐isomiddleearthjeweledtech-agentic-frameworklocally-uncensoredmirothinkeropenhumanquran-databaseunderstand-anythingDecisões importantes (ver session log pra detalhes)
agents-marketplaceporque traz 100+ SKILL.md bundled com author signal forte (Google oficial)#datasetintroduzida como metadata-only (semtags/dataset.mdpróprio ainda)Test plan
docs/registry/INDEX.mde verificar que as 14 linhas estão em ordem alfabética sensataos-self-testskill após merge pra validar cross-referencesIndependente do Sprint 0
Esta PR não toca nada de
course/,course/systems/, ou da branchsprint-0-systems-html(PR #9). Pode mergear em qualquer ordem.🤖 Generated with Claude Code
Summary by CodeRabbit