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/davesheffer/hunch/auditgit clone --depth 1 https://github.com/davesheffer/hunchWhat 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 | $0.00022 | $0.00273 |
| Opus 5 | $0.00011 | $0.00137 |
| Sonnet 5 | $0.00004 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
audit 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 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.
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.
What it actually says
Audit $ARGUMENTS and record what you find into Hunch's graph.
- Run the actual check (query/grep/script) — a finding needs EVIDENCE: the exact command you ran plus representative output. Never record a finding you didn't observe.
- For each REAL gap:
hunch_record_findingwith title, observation, evidence, affected_files/affected_symbols, severity. It grounds future edits to those files automatically. - If the gap violates an existing invariant, link it via
violates_constraint. If the RULE itself is unrecorded, capture the rule FIRST (hunch_record_correction), then link it. - If the audit is re-runnable, capture the procedure as a runbook and set
methodto its rb_* id — that makes the finding re-verifiable, not folklore. - Triage with me inline: open (default) / accepted-risk / scheduled. NEVER mark resolved without the fixing commit (
resolved_commit). - Report: findings recorded (ids), what was checked and came back clean, and what stays unverified.
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 · 14 lines · 22 tokens per session scan A cbad55e25d6a
audit is a command published in the GitHub repository davesheffer/hunch (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 273 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 commands, from other repositories
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).
dev-planner
Generate or update DEV-PLAN.md with phased development plan from Product-Spec.md.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.