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/capturegit 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 | $0.00021 | $0.00244 |
| Opus 5 | $0.00010 | $0.00122 |
| Sonnet 5 | $0.00004 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
capture 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
Capture the decision for $ARGUMENTS into Hunch's graph.
- Call
hunch_capture_decision(topic?, seed?)— it returns the grilling protocol and a capture-session token. - Run the GRILLING LOOP: one focused question at a time. Push back on hand-wavy answers. Resolve every branch before committing — an unexamined decision poisons the graph.
- Confirm the TOPIC anchor with me before committing. One topic per decision; if it spans two, split into two captures.
- Capture REJECTED alternatives explicitly (what, and why not) — this is what makes the decision enforceable (Veto/drift check against it).
- Commit with
hunch_record_decision, passingcapture_token(from step 1) and the confirmedtopic. The artifact is the graph write, not prose. - On CONFLICT for the topic, do NOT auto-supersede — Hunch refuses and presents both; let me choose supersede (link) / split the topic / discard.
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 · 12 lines · 21 tokens per session scan A 7957f7ec519a
capture is a command published in the GitHub repository davesheffer/hunch (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 21 tokens to every session and 244 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
OPSX: Bulk Archive
Archive multiple completed changes at once.
doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing).
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).
revoke
Mark a subscribetome-managed API key as revoked.