Borrowing it
Nothing to install: this file belongs to davesheffer/hunch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/davesheffer/hunch/main/.claude/commands/hunch-fix.mdgit 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/hunch-fix)<a href="https://agentmods.dev/commands/davesheffer/hunch/hunch-fix"><img src="https://agentmods.dev/badge/commands/davesheffer/hunch/hunch-fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/davesheffer/hunch/hunch-fix"><img src="https://agentmods.dev/badge/commands/davesheffer/hunch/hunch-fix.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.00199 |
| Opus 5.5 | $0.00007 | $0.00080 |
| Sonnet 5.5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
hunch-fix 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 1mo 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
We are fixing: $ARGUMENTS
Follow the Hunch-grounded workflow (DESIGN §5) — do NOT skip the memory lookups:
hunch_bug_lineage("$ARGUMENTS")— has this class of bug happened before? what was the root cause and the fix?- Identify the suspect symbol/file, then
hunch_get_dependents(<symbol>)to learn the blast radius. hunch_check_constraints(<scope>)— list invariants you must preserve.- Propose a fix that honors past root causes AND constraints. Apply it and run the tests.
- If the fix encodes a non-trivial choice,
hunch_record_decision(...)so the next session is grounded in it.
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.
- 1mo ago First seen · 14 lines · 17 tokens per session scan A 33a1b1a9658f
hunch-fix is a command published in the GitHub repository davesheffer/hunch (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 17 tokens to every session and 199 once invoked, about $0.0001 per session on Opus 5.5. 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
ABCoder: Recheck
Validate CODETASK technical feasibility with critical analysis using mcpabcoder.
simplify-analyze
Analyze code for simplification opportunities. Part of simplify- family.
simplify
Orchestrates code simplification via verified transformations. Delegates to simplify-analyze, simplify-verify, and simplify-transform.
layer-check
You are the Three-Layer Enforcement Agent, the strict validator that ensures every feature is REAL across all tiers: Database, Backend, and Frontend. You do not accept incomplete implementations.
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
review-hard
Review the current task changes for correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Use when a slice or task-level implementation was completed, the user wants a focused engineering risk review before closure or PR prep, or meaningful issues…