vouch-resolve-issue

A command for resolving a GitHub issue using information stored in vouch's knowledge base, or KB. It also proposes reviewed knowledge that could help future contributors.

In plain words
What is it for?
Reading an issue, checking related knowledge, reproducing the bug with tests, choosing a small fix, and proposing cited claims for maintainer review.
Why use it?
It reduces the need to search scattered project history and helps preserve the cause and solution after a bug is fixed.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/vouchdev/vouch/vouch-resolve-issue
Clone the repo
git clone --depth 1 https://github.com/vouchdev/vouch

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00274
Opus 5 $0.00007 $0.00137
Sonnet 5 $0.00003 $0.00055
Haiku 4.5 $0.00001 $0.00027

Measured 2d ago against content hash 2498de07cf84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vouch-resolve-issue 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.

adapters/claude-code/.claude/commands/vouch-resolve-issue.md · 28 lines

What it actually says

/vouch-resolve-issue

Wire vouch's kb_context into an issue-resolution flow: the KB should inform the fix, and the act of solving should propose new claims that make the next contributor faster.

Steps:

  1. Parse $ARGUMENTS as a GitHub issue URL or <owner>/<repo>#<num> shorthand. If neither, ask for clarification.
  2. kb_context with the issue title + body — what does the KB already know about this area? Show the top 5 claims.
  3. Read the relevant code paths.
  4. Propose the smallest fix (run the project's tests first to confirm the bug reproduces).
  5. After the fix is committed, propose at most three new claims via kb_propose_claim that capture:
    • the root cause in one sentence (cited by the offending file:line),
    • the chosen fix pattern (cited by the patch commit), and
    • any policy/precedent established (only if novel).

Do not auto-approve. Leave the proposals in .vouch/proposed/ for the maintainer to review with vouch approve after the PR merges.

Changes

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.

  1. 2d ago First seen · 28 lines · 14 tokens per session scan A 2498de07cf84

Subscribe to this mod's changes

vouch-resolve-issue is a command published in the GitHub repository vouchdev/vouch (91 stars, last pushed 10d ago), licensed MIT. It adds 14 tokens to every session and 274 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 2026-08-30.