resolve-issue

resolve-issue is a command for Claude Code from kid-sid/claude-spellbook. It costs 0 tokens per session (689 once invoked), scanned A, original, MIT.

A command that takes a GitHub issue, a tracked report of a software problem or request, and carries out the described fix. It then records the result on GitHub and closes the issue.

In plain words
What is it for?
Use it with an issue number to fetch the issue, locate the relevant code, apply the fix, comment on what changed, and close the issue.
Why use it?
It gathers the issue details and discussion in one workflow, reducing the chance of missing reproduction steps or agreed limits. Optional guidance can restrict which part is changed.

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/kid-sid/claude-spellbook/resolve-issue
Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

Made for: Claude Code.

Wrote 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.

agentmods badge for resolve-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/resolve-issue.svg)](https://agentmods.dev/commands/kid-sid/claude-spellbook/resolve-issue)
Your own site
<a href="https://agentmods.dev/commands/kid-sid/claude-spellbook/resolve-issue"><img src="https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/resolve-issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 689 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 $0.00000 $0.00689
Opus 5 $0.00000 $0.00345
Sonnet 5 $0.00000 $0.00138
Haiku 4.5 $0.00000 $0.00069

Measured 5d ago against content hash 2c1f45b67688, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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.

.claude/commands/resolve-issue.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fetch a GitHub issue, apply the fix, comment with what was done, and close the issue.

Usage: /resolve-issue <#number> [optional guidance]

Examples:

  • /resolve-issue #12 — read the issue and fix it as described
  • /resolve-issue #12 Only fix part 1 — adding the null check in auth.py — fix with scoped guidance

Instructions

1. Parse the arguments

From $ARGUMENTS:

  • Extract the issue number — accept #3, 3, or GH-3 forms
  • Everything after the number is optional guidance that narrows the scope or hints at the approach

2. Read the issue

gh issue view <number> --json number,title,body,labels,assignees,comments

Read the full issue body and all comments. Understand:

  • What is broken / what is requested
  • Any reproduction steps, error messages, or stack traces in the body
  • Prior discussion in comments that narrows the fix

If the issue is already closed, tell the user and stop.

3. Locate the relevant code

Search the codebase for files, functions, or patterns mentioned in the issue. Use the optional guidance to narrow scope — if the user said "only fix part 1" or "just the auth.py null check", limit your changes accordingly.

Do not make changes outside the scope described by the issue + guidance.

4. Apply the fix

Make the minimal correct change. Follow the conventions already present in the file. Do not refactor surrounding code, add unrelated features, or touch files not relevant to the fix.

If the fix requires multiple steps (e.g., schema migration + code change), lay them out and apply in order.

5. Verify

If the repo has a test command discoverable from Makefile, package.json, or pyproject.toml, run the relevant tests for the changed files:

# Examples — use what fits the project
make test
npm test -- --testPathPattern=<changed file>
pytest <changed file> -x
go test ./...

If tests fail, fix them before proceeding.

6. Comment on the issue

gh issue comment <number> --body "$(cat <<'EOF'
## Fix applied

<one sentence describing what was changed and why it resolves the issue>

**Files changed:**
- `path/to/file.py` — <what changed>

**Approach:** <brief rationale — why this fix rather than alternatives>

**Testing:** <what was run to verify, or "no automated tests exist for this path">
EOF
)"

Read the full file on GitHub · 93 lines

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. 5d ago First seen · 93 lines · 0 tokens per session scan A 2c1f45b67688

Subscribe to this mod's changes

resolve-issue is a command published in the GitHub repository kid-sid/claude-spellbook (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 689 tokens. 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.