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/healgit clone --depth 1 https://github.com/davesheffer/hunchWrote 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/commands/davesheffer/hunch/heal)<a href="https://agentmods.dev/commands/davesheffer/hunch/heal"><img src="https://agentmods.dev/badge/commands/davesheffer/hunch/heal.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 | $0.00021 | $0.00225 |
| Opus 5 | $0.00010 | $0.00112 |
| Sonnet 5 | $0.00004 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
heal 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 3d 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
Reconcile decision-grounding drift for $ARGUMENTS (or the whole repo).
- Run
hunch drift(orhunch heal) to list doc≠graph anchor-stale sections — a file still anchored to a superseded decision while a current one exists. Only explicit topic anchors fire; never a semantic guess. - For each, assume the DOC is stale first (Heal A). Propose an edit bringing the file to the CURRENT decision; show it as a diff and wait for my confirm. Never rewrite prose silently.
- Only if I explicitly say "the DECISION is stale, not the doc" (Heal B): run /capture to record a superseding decision, then return to step 2 — the prose re-derives from the new decision as a separate confirm.
- Report: healed (Heal A), superseded (Heal B), skipped. Never touch the graph except via an explicit Heal B capture.
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.
- 3d ago First seen · 10 lines · 21 tokens per session scan A c181b27e6d5c
heal is a command published in the GitHub repository davesheffer/hunch (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 225 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
memstack-search
Search MemStack memory for past sessions, insights, and project context.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
check
Run mneme check against a file or proposed change.
memory-review
Display current memory state with timestamps, sizes, and staleness indicators.
index
Create persistent project understanding via PROJECTMAP.md.
context
上下文管理，加载项目信息（会话级，另见 /cc-best:memory 管理持久记忆）.