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 commands/vorobiovd/air/learngit clone --depth 1 https://github.com/VorobiovD/airWhat 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 | $0.00028 | $0.08603 |
| Opus 5 | $0.00014 | $0.04301 |
| Sonnet 5 | $0.00006 | $0.01721 |
| Haiku 4.5 | $0.00003 | $0.00860 |
Grade C, and why
learn scanned grade C with 1 finding 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 2d 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.
find /tmp -maxdepth 1 -name 'air-*' -mtime +1 -exec rm -rf {} + 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fetch REVIEW.md from the wiki, clean it up using AI, generate REVIEW-HISTORY.md from PR comment history, and push both back.
Note: /air:review auto-triggers this command every 15 reviews (default; a repo can retune the count with AIR_LEARN_REVIEWS_THRESHOLD) or every 14 days — whichever comes first. You can also run it manually for immediate cleanup.
Store-backed repos (managed/headless fleet): when a repo's patterns live in an Anthropic memory store (the source of truth), the canonical learn is the cloud/client
air-learner(managedlearn.py, or the MA-independentmanaged/learn_headless.py), which curates the store; a deterministic Python step (managed/render_store_to_wiki.py) then exports the git-wiki mirror. This CLI command never reads or renders the store — it operates on the git wiki directly, so on a store-backed repo its writes would be overwritten by the next render. Step 1 now DETECTS a store mirror (via the render's banner — no API key needed) and STOPS, instead of relying onfind-store(which is blank when the localANTHROPIC_API_KEYcan't see the repo's store). Reserve this CLI flow for legacy wiki-only repos.
Flags:
--dry-run— preview changes without pushing to wiki--history-only— only regenerate REVIEW-HISTORY.md, don't touch REVIEW.md--refresh-profile— re-run the full Opus deep scan for PROJECT-PROFILE.md + GLOSSARY.md (same as first-run discovery). Use when the project has changed significantly (new language, new service, major restructure). Overwrites existing profile and glossary with fresh scan results.
Setup
air uses the gh CLI. Derive PLATFORM_DOMAIN from the remote host (same as review.md "Setup"):
REMOTE_URL=$(git remote get-url origin 2>/dev/null)
if [[ "$REMOTE_URL" =~ ^https?://([^/]+)/ ]]; then PLATFORM_DOMAIN="${BASH_REMATCH[1]}"
elif [[ "$REMOTE_URL" =~ ^git@([^:]+): ]]; then PLATFORM_DOMAIN="${BASH_REMATCH[1]}"
else PLATFORM_DOMAIN="github.com"; fi
Step 0: Initialize Session Temp Directory
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.
- 2d ago First seen · 499 lines · 0 tokens per session scan C 0fd7b28ea788
learn is a command published in the GitHub repository VorobiovD/air (5 stars, last pushed 7d ago), licensed MIT. It adds 28 tokens to every session and 8,603 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review
Review PRs against the conventions learned from each repo — 1 post per PR, findings tagged by severity, code left untouched.
release-now
Create a git tag + GitHub Release for open-pr — an official release if standing on main, an RC if standing on a branch with an open PR (a dev tool specific to this repo, not shipped in the plugin).
fix
Act on the findings a review left on a PR — takes or declines each by severity, edits code at pwd to match the project, 1 commit, replies once pushed.
feedback
Report a problem with the open-pr plugin itself, or ask for a change, on its public issue tracker. Reads no PR; writes nothing in your repo.
upgrade
Bring every per-repo config found below pwd up to the schema this build expects. Takes no PR.
smoke
Smoke-test the agent-smith CLI binary + docker-compose for api-scan / security-scan / fix-bug. Catches regressions that escape the unit test suite.