Remove dollar-denominated cost references from agentic-ops workflows and docs

Author: mnkiefer

.github/workflows/agentic-token-audit.md

@@ -79,7 +79,7 @@ You are the Agentic Workflow Token Auditor — a workflow that tracks daily toke
 
 1. Parse the pre-downloaded agentic workflow logs and compute per-workflow token usage metrics.
 2. Persist today's snapshot to repo-memory so the optimizer (and future runs of this audit) can read historical data.
-3. Publish a concise audit issue summarizing today's usage, trends, and cost highlights.
+3. Publish a concise audit issue summarizing today's usage and trend highlights.
 
 ## Data Sources
 
@@ -89,7 +89,7 @@ The workflow logs are at `/tmp/gh-aw/token-audit/workflow-logs.json`. The file i
 
 ```json
 {
-  "summary": { "total_runs": N, "total_tokens": N, "total_cost": F, ... },
+  "summary": { "total_runs": N, "total_tokens": N, ... },
   "runs": [ ... ],
   "tool_usage": [ ... ],
   "mcp_tool_usage": { ... },
@@ -104,8 +104,7 @@ Each element of `.runs` is a `RunData` object with (among others):
 | `workflow_name` | string | Human-readable name |
 | `workflow_path` | string | `.github/workflows/....lock.yml` |
 | `token_usage` | int | Total tokens (`omitempty` — treat missing/null as 0) |
-| `effective_tokens` | int | Cost-normalized tokens |
-| `estimated_cost` | float | USD cost (`omitempty` — treat missing/null as 0) |
+| `effective_tokens` | int | Normalized token metric |
 | `action_minutes` | float | Billable GitHub Actions minutes |
 | `turns` | int | Number of agent turns |
 | `duration` | string | Human-readable duration |
@@ -129,8 +128,8 @@ Write a Python script to `/tmp/gh-aw/token-audit/process_audit.py` and run it. T
 1. Load `/tmp/gh-aw/token-audit/workflow-logs.json` and extract `.runs`.
 2. Filter to `status == "completed"` runs only.
 3. Group by `workflow_name` and compute per-workflow aggregates:
-   - `run_count`, `total_tokens`, `avg_tokens`, `total_cost`, `avg_cost`, `total_turns`, `avg_turns`, `total_action_minutes`, `error_count`, `warning_count`
-4. Compute an overall summary: total runs, total tokens, total cost, total action minutes.
+   - `run_count`, `total_tokens`, `avg_tokens`, `total_turns`, `avg_turns`, `total_action_minutes`, `error_count`, `warning_count`
+4. Compute an overall summary: total runs, total tokens, total action minutes.
 5. Sort workflows descending by `total_tokens`.
 6. Save the result to `/tmp/gh-aw/token-audit/audit_snapshot.json` with this shape:
 
@@ -141,7 +140,6 @@ Write a Python script to `/tmp/gh-aw/token-audit/process_audit.py` and run it. T
   "overall": {
     "total_runs": N,
     "total_tokens": N,
-    "total_cost": F,
     "total_action_minutes": F
   },
   "workflows": [
@@ -150,8 +148,6 @@ Write a Python script to `/tmp/gh-aw/token-audit/process_audit.py` and run it. T
       "run_count": N,
       "total_tokens": N,
       "avg_tokens": N,
-      "total_cost": F,
-      "avg_cost": F,
       "total_turns": N,
       "avg_turns": F,
       "total_action_minutes": F,
@@ -163,15 +159,15 @@ Write a Python script to `/tmp/gh-aw/token-audit/process_audit.py` and run it. T
 }
 ```
 
-Handle null/missing `token_usage` and `estimated_cost` by treating them as 0.
+Handle null/missing `token_usage` by treating them as 0.
 
 ## Phase 2 — Persist Snapshot to Repo-Memory
 
 1. Read the snapshot from `/tmp/gh-aw/token-audit/audit_snapshot.json`.
 2. Copy it to `/tmp/gh-aw/repo-memory/default/YYYY-MM-DD.json` (today's UTC date).
 3. This file is what the optimizer workflow reads to identify high-usage workflows.
 
-Also maintain a rolling summary file at `/tmp/gh-aw/repo-memory/default/rolling-summary.json` that contains an array of daily overall totals (date, total_tokens, total_cost, total_runs, total_action_minutes) for the last 90 entries. Load the existing file, append today's entry, trim to 90, and save.
+Also maintain a rolling summary file at `/tmp/gh-aw/repo-memory/default/rolling-summary.json` that contains an array of daily overall totals (date, total_tokens, total_runs, total_action_minutes) for the last 90 entries. Load the existing file, append today's entry, trim to 90, and save.
 
 Do not append a synthetic zero-valued entry to `rolling-summary.json` when either of these conditions is true:
 
@@ -218,15 +214,14 @@ Create an issue with these sections:
 - **Period**: last 24 hours (YYYY-MM-DD to YYYY-MM-DD)
 - **Total runs**: N
 - **Total tokens**: N (formatted with commas)
-- **Total cost**: $X.XX
 - **Total Actions minutes**: X.X min
 - **Active workflows**: N
 
 ### 🏆 Top 5 Workflows by Token Usage
 
-| Workflow | Runs | Total Tokens | Avg Tokens | Total Cost | Avg Cost |
-|---|---|---|---|---|---|
-| ... | ... | ... | ... | ... | ... |
+| Workflow | Runs | Total Tokens | Avg Tokens |
+|---|---|---|---|
+| ... | ... | ... | ... |
 
 ### 📈 Trends
 
@@ -236,7 +231,7 @@ Embed chart images using uploaded asset URLs when available:
 
 ![Historical Token Trend](UPLOAD_URL_TREND_PLACEHOLDER)
 
-Summarize token and cost changes from `rolling-summary.json` when historical data is available.
+Summarize token changes from `rolling-summary.json` when historical data is available.
 
 <details>
 <summary><b>Full Per-Workflow Breakdown</b></summary>

.github/workflows/agentic-token-optimizer.lock.yml

@@ -72,7 +72,6 @@ steps:
             | {
                 workflow_name: .workflow_name,
                 tokens: (.token_usage // 0),
-                cost: (.estimated_cost // 0),
                 turns: (.turns // 0),
                 action_minutes: (.action_minutes // 0)
               }
@@ -83,7 +82,6 @@ steps:
               run_count: length,
               total_tokens: (map(.tokens) | add),
               avg_tokens: ((map(.tokens) | add) / length),
-              total_cost: (map(.cost) | add),
               total_turns: (map(.turns) | add),
               total_action_minutes: (map(.action_minutes) | add)
             })
@@ -111,7 +109,7 @@ steps:
 
 # Agentic Workflow Token Usage Optimizer
 
-You are the Agentic Workflow Token Optimizer. Pick one high-cost workflow, audit recent runs, and create a conservative optimization issue with measurable savings. Your recommendations may include prompt, tool, reliability, setup-prefix, and inline sub-agent improvements when the evidence supports them.
+You are the Agentic Workflow Token Optimizer. Pick one high-token workflow, audit recent runs, and create a conservative optimization issue with measurable improvements. Your recommendations may include prompt, tool, reliability, setup-prefix, and inline sub-agent improvements when the evidence supports them.
 
 ## Objectives
 
@@ -154,7 +152,7 @@ Prefer `--jq` on `gh api` calls over a separate `| jq` step when the filter is s
 - `/tmp/gh-aw/repo-memory/default/YYYY-MM-DD.json`: daily audit snapshots.
 - `/tmp/gh-aw/repo-memory/default/optimization-log.json`: prior optimizations (if present).
 
-Treat missing numeric fields (`token_usage`, `estimated_cost`, `turns`, `action_minutes`) as `0`.
+Treat missing numeric fields (`token_usage`, `turns`, `action_minutes`) as `0`.
 
 ## Phase 1 — Select Target
 
@@ -168,7 +166,6 @@ Then collect run-level data for the selected workflow:
 
 - run count
 - total and average tokens
-- total and average cost
 - total and average turns
 - conclusions/error patterns
 
@@ -282,7 +279,7 @@ Create one issue with:
 
 - **Target workflow + reason selected**
 - **Analysis period + runs analyzed**
-- **Token profile table** (total tokens, avg tokens/run, total cost, avg turns/run, cache efficiency)
+- **Token profile table** (total tokens, avg tokens/run, avg turns/run, cache efficiency)
 - **Ranked recommendations** with:
   - title
   - estimated token savings per run

.github/workflows/agentic-token-optimizer.md

@@ -174,7 +174,7 @@ jobs:
             await main();
 
       - name: Install gh-aw
-        uses: github/gh-aw-actions/setup-cli@bc56a0cad2f450c562810785ef38649c04db812a # v0.72.1
+        uses: github/gh-aw-actions/setup-cli@v0.72.1
         with:
           version: v0.72.1
 
@@ -309,7 +309,7 @@ jobs:
             await main();
 
       - name: Install gh-aw
-        uses: github/gh-aw-actions/setup-cli@bc56a0cad2f450c562810785ef38649c04db812a # v0.72.1
+        uses: github/gh-aw-actions/setup-cli@v0.72.1
         with:
           version: v0.72.1
 
@@ -355,7 +355,7 @@ jobs:
             await main();
 
       - name: Install gh-aw
-        uses: github/gh-aw-actions/setup-cli@bc56a0cad2f450c562810785ef38649c04db812a # v0.72.1
+        uses: github/gh-aw-actions/setup-cli@v0.72.1
         with:
           version: v0.72.1
 
@@ -489,7 +489,7 @@ jobs:
             await main();
 
       - name: Install gh-aw
-        uses: github/gh-aw-actions/setup-cli@bc56a0cad2f450c562810785ef38649c04db812a # v0.72.1
+        uses: github/gh-aw-actions/setup-cli@v0.72.1
         with:
           version: v0.72.1
 

.github/workflows/agentics-maintenance.yml

@@ -209,7 +209,7 @@ The notes must be user-facing:
 Selection rubric for whether a change belongs in the release notes or changelog:
 
 - include it when a user would notice it by using the workflow, reading its issue/report output, configuring it, upgrading it, or debugging it
-- include it when it changes expectations around compatibility, migration, deprecation, stability, security, or operating cost
+- include it when it changes expectations around compatibility, migration, deprecation, stability, security, or operating overhead
 - omit it when it only affects how the repository is built, tested, compiled, organized, or maintained internally
 - omit it when it is merely a prerequisite for other work and has no standalone user-facing effect
 - collapse related low-level changes into one user-facing outcome when they support the same improvement