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 skills add Aimeerrhythm/enterprise-change-workflow --skill risk-classifiergit 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/risk-classifier)<a href="https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/risk-classifier"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/risk-classifier.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 | $0.00052 | $0.00744 |
| Opus 5 | $0.00026 | $0.00372 |
| Sonnet 5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
risk-classifier 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 7d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Classifier
Overview
Classify risk level (P0~P3) for any requirement or feature change, driving the depth of downstream workflow.
Output language: Read ecw.yml → project.output_language. All artifact headings, table headers, and labels follow this language. session-state.json field keys stay English (machine-parsed).
Core Principle: The process for changing a log statement should not be as heavy as changing inventory deduction logic.
Announce at start: "Using ecw:risk-classifier to classify change risk level."
When to Use
- User proposes any requirement, feature change, or code modification
- User says "I want to...", "need to change...", "add a feature...", "implement..."
- Must execute before ecw:requirements-elicitation
When NOT to use:
- Pure code reading/analysis/questions ("What does this class do?")
- User explicitly says "use PX" (manually specified level, skip auto-classification)
- Initial risk assessment already completed in current session and level not contested
- Bug fixes — use
ecw:systematic-debuggingas the entry point instead
Initial Risk Assessment
Read ./prompts/risk-assessment-guide.md for assessment steps and output format.
State Persistence
Read ./session-state-format.md to write session state — includes JSON schema, workflow ID generation, and conflict detection. On conflict: regenerate workflow ID up to max 3 attempts before prompting user.
routing[0] values:
ecw:requirements-elicitation— single-domain requirementecw:domain-collab— cross-domain requirement (P0 or P2)ecw:writing-plans— P2 single-domain entry (no requirement analysis needed)- (omit routing field entirely) — P3 direct implementation
Why session-state.json format is non-negotiable: the auto-continue hook reads routing and next to inject the next skill in the chain. If required fields are missing or the JSON is malformed, the hook silently no-ops — the model loses routing guidance and the workflow chain breaks. Conform to ./session-state-format.md exactly; do not improvise field names or omit required fields.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 65 lines · 52 tokens per session scan A db629c59279b
risk-classifier is a skill published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 744 once invoked, about $0.0003 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
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
nazgul:heartbeat
Run one Nazgul automation-heartbeat tick — triages the work inbox and auto-starts the next objective if idle. Opt-in and default-off; fired by an optional Claude Code native scheduled agent (routine) or run by hand. Use when asked to "run a heartbeat tick", "check the inbox", or to test/debug the heartbeat.
fix
Systematic debugging — investigate, hypothesize, fix, verify. No fixes without root cause.
retro
Post-ship retrospective — what worked, what didn't, root causes, action items.
qa
QA testing — browse like a real user, document bugs, report only. Never fixes.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.