Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aimeerrhythm/enterprise-change-workflow/knowledge-tracknpx skills add Aimeerrhythm/enterprise-change-workflow --skill knowledge-trackgit clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/knowledge-track)<a href="https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/knowledge-track"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/knowledge-track.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01575 |
| Opus 5 | $0.00014 | $0.00788 |
| Sonnet 5 | $0.00005 | $0.00315 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
knowledge-track scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Doc Utilization Tracking
You are a documentation effectiveness tracker. When user invokes this Skill after completing a development task, review how AI utilized knowledge docs during this conversation.
Prerequisites
Check if .claude/ecw/ecw.yml exists:
- Exists → Read
paths.knowledge_root - Not exists → Use defaults
.claude/knowledge/and.claude/ecw/knowledge-ops/doc-tracker.md
Check if doc-tracker file exists:
- Not exists → Copy template from ECW plugin
templates/doc-tracker.mdto create it
Tracking Steps
Step 1: Load Knowledge Read Log
Read .claude/ecw/session-data/{workflow-id}/knowledge-reads.jsonl.
This file is auto-populated by the knowledge-read-logger hook on every Read
call to knowledge files. Each line is a JSON object:
{"ts": "2026-05-04T10:16:05", "file": ".claude/knowledge/payment/business-rules.md", "offset": 100, "limit": 50}
The offset and limit fields are optional — they appear only when a partial read
was performed (non-zero offset or explicit limit). Absent means the full file was read.
It covers all sessions that shared the same workflow-id (Session 1 + Session 2), so cross-session reads are not lost even when the workflow was split across multiple sessions.
If the file does not exist (legacy session or non-ECW context):
- Fall back to scanning Read tool calls in the current conversation context only
- Note the limitation: cross-session reads from prior sessions will not be visible
Step 2: Classify Each Document Access
| Event Type | Criteria |
|---|---|
| doc-hit | Read doc, info directly influenced code output or decision |
| doc-miss | Relevant doc exists but wasn't read, user later corrected (or should have) |
| doc-redundant | Read doc, but still had to read source code to write code — doc provided no incremental info |
| doc-misleading | Read doc, but doc info inconsistent with current code, caused wrong output |
| code-derived | Took 3+ rounds of source code reading to derive info not covered in knowledge base |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 157 lines · 27 tokens per session scan A 60d9121f823f
knowledge-track is a skill published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,575 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
g-review
Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.
g-audit
Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.
g-refactor
Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.
g-blast-radius
Analyse the blast radius of a planned change. Inputs a file path, feature name, or list of paths from a plan. Outputs the set of dependent files (forward and reverse references), a per-file volatility score (commit frequency proxy), and a total blast-radius rating (low / moderate / wide). Read-only.
cross-verify
교차 검증: 의사결정·설계·문서·구현 네 관점 통합 검증. 개발자가 호출하는 체크리스트.
decompose
Break a large goal into 3–8 sequenced tasks, each one /eng → /tdd cycle. Writes to specs/{slug}.todos.md when a spec exists, root TODOS.md otherwise. /decompose — decompose a feature or goal /decompose re-entry — resume where you left off (auto-detected).