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/akopichin/afm/verifynpx skills add akopichin/afm --skill verifygit clone --depth 1 https://github.com/akopichin/afmWrote 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/akopichin/afm/verify)<a href="https://agentmods.dev/skills/akopichin/afm/verify"><img src="https://agentmods.dev/badge/skills/akopichin/afm/verify.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 | $0.00024 | $0.01308 |
| Opus 5 | $0.00012 | $0.00654 |
| Sonnet 5 | $0.00005 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade C, and why
verify scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Docker mode mounts `$(pwd)` into the container 1:1. If you `rm -rf .afm/runs` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
dashboard through the browser or curl. This exercises the real Go How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying afm end-to-end
Build → run a flow.yaml with a mock agent (no real API calls) → drive the
dashboard through the browser or curl. This exercises the real Go
orchestrator + pkg/server + dashboard, not just go test.
Build
make docker-build # tags akopichin/afm:latest from Dockerfile.runtime, local single-arch
Sanity check: docker run --rm akopichin/afm:latest --version (note: the
entrypoint IS afm, so pass flags directly — afm afm --version is wrong).
Mock agent instead of real claude
Real claude needs CLAUDE_CODE_OAUTH_TOKEN/ANTHROPIC_API_KEY inside
Docker (macOS Keychain isn't reachable from the Linux container) — skip
this entirely for orchestrator-only smoke tests with a bash mock agent that
speaks claude's stream-json protocol:
jq -nc --arg t "some text" '{type:"assistant",message:{content:[{type:"text",text:$t}]}}'
Phase is inferred from context afm itself provides, not from prompt wording:
- implementation: the prompt always embeds a literal
Stage directory for .done file: <path>line (pkg/orchestrator/agents.gorunImplementationAgent) → write.donethere. - autonomous (
agents: [auto]):AFM_STAGE_DIRenv var is set for this phase and the prompt mentionsexecution_summary.md→ write it there. - interactive dialog (any phase with
AFM_STAGE_DIRset, i.e.interactive: truestages): write<phase>.<id>.question.jsoninto$AFM_STAGE_DIR, poll for<phase>.<id>.answer.json, then proceed. - default (non-interactive planning/review): just emit assistant text
with
## Tasks/## Assumptions/## Acceptance Criteriaheadings —RunPlanningwrites the collected text toplan.mditself when noWritetool_use event matches;RunAgent(review) ignores the text entirely.
One unified script covers every stage type — see the phase-inference order above (check implementation's marker first, then autonomous's, then interactive, then default).
Project-level .afm/config.yaml for a smoke-test project dir
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.
- 4d ago First seen · 112 lines · 24 tokens per session scan C 412193f7218b
verify is a skill published in the GitHub repository akopichin/afm (11 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,308 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…