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 instructions/davesheffer/hunch/agents-mdgit 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 | $0.01510 | $0.01510 |
| Opus 5 | $0.00755 | $0.00755 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
hunch AGENTS.md 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.
This is a copy
98% identical to hunch copilot-instructions.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
🧠 Hunch (Engineering Memory)
This repo has Hunch — a curated graph of why the code is the way it is (decisions, bug history, invariants). It currently holds 193 decisions, 2 bugs, 10 constraints, 19 components, 3 policies, 1 open findings.
Consult Hunch via the hunch_* MCP tools — pick by MOMENT, not from memory:
Orient (session/task start):
hunch_context(target)— the minimal relevant slice for what you're about to do; a task phrase falls back to the closest graph matches. Call FIRST.hunch_structure(target?)— the indexed shape of the repo/dir/file/symbol — orient from the graph, not grep rounds.hunch_runbook(task)— the proven steps for a recurring task, before re-deriving them.hunch_escalations()— the decisions only the HUMAN can make (including one exact imported ADR at a time, topic conflicts, and policy calls). Normally empty; when it isn't, ASK the user inline — an entry is a question, silence is never approval. Apply an ADR answer only throughhunch_review_imported_adrwith its printed source and review hashes.hunch now(CLI) — recent decisions + the live roadmap;hunch log— the memory-move timeline (every capture/adopt/supersede/prune/repair, each revertable).
Before designing / choosing an approach:
hunch_why(target)— why a file/symbol is shaped this way (decisions, bugs, constraints) — including what was already REJECTED.hunch_current_decision(topic)— the one live answer for a topic (history + rejected included).hunch_bug_lineage(symptom_or_symbol)— has this failed before? what was the root cause?hunch_compare(candidates)— rank candidate branches/commits by fewest invariant hits.hunch_query(query)— free-text search when nothing above fits.
Before editing:
hunch_check_constraints(scope)andhunch_get_dependents(symbol)/hunch_blast_radius(target)— invariants in scope + who you'd break. (The pre-edit hook injects this per file automatically; call these for PLANNING breadth.)hunch_findings(scope?)— known-but-unfixed gaps in the area (past audits, measurements, incidents) so you inherit them instead of re-discovering them.
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 · 55 lines · 1,510 tokens per session scan A 693c4071f8a8
hunch AGENTS.md is an instructions file published in the GitHub repository davesheffer/hunch (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,510 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to hunch copilot-instructions.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
opensrc AGENTS.md
Instructions for vercel-labs/opensrc, covering agents.md, monorepo structure, cli (packages/opensrc), docs (apps/docs) and releasing.
nanocoder CLAUDE.md
Claude Code instructions for Nano-Collective/nanocoder, covering claude.md, development commands, build and run, testing (run before committing) and individual test commands.
nanocoder AGENTS.md
AGENTS.md instructions for Nano-Collective/nanocoder, covering agents.md, project overview, architecture, key files and development commands.
vibe-coding-repository-standard AGENTS.md
Instructions for cz1993/vibe-coding-repository-standard, covering vcrs repository instructions, purpose, communication, change discipline and privacy and safety.
tokenmaxxing AGENTS.md
Instructions for 851-labs/tokenmaxxing, covering repository instructions, effect error style, export style, conventions and cli output style.
agent-toolkit AGENTS.md
Instructions for Arnosdeus/agent-toolkit, covering shared agent instructions, repository inspection, existing architecture, frontend and ui quality and testing.