Borrowing it
Nothing to install: this file belongs to dgenio/contextweaver. 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/dgenio/contextweaver/main/.github/prompts/fix-bug.prompt.mdgit clone --depth 1 https://github.com/dgenio/contextweaverWrote 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/dgenio/contextweaver/fix-bug)<a href="https://agentmods.dev/commands/dgenio/contextweaver/fix-bug"><img src="https://agentmods.dev/badge/commands/dgenio/contextweaver/fix-bug/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/dgenio/contextweaver/fix-bug"><img src="https://agentmods.dev/badge/commands/dgenio/contextweaver/fix-bug.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 | $0.00013 | $0.00443 |
| Opus 5.5 | $0.00005 | $0.00177 |
| Sonnet 5.5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
fix-bug 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
Fix a Bug
Follow these steps in order. Each step has a clear success criterion.
References
AGENTS.md— module map, hard rules, strong patterns, coding style.github/instructions/context.instructions.md— context engine invariants.github/instructions/routing.instructions.md— routing engine invariants.github/instructions/sensitivity.instructions.md— security-grade sensitivity codedocs/agent-context/architecture.md— architectural boundaries and tradeoffsdocs/agent-context/invariants.md— hard constraints and forbidden shortcuts
Steps
-
Write a failing test that reproduces the bug. Add the test to
tests/test_<module>.pybefore touching production code. Success:make testfails only on the new test. -
Identify the root-cause module. Use
AGENTS.md's module map anddocs/agent-context/architecture.mdto trace the defect to its origin. Checkdocs/agent-context/invariants.mdto confirm the fix won't violate a hard constraint. Success: root-cause file and line range are known. -
Apply the minimal fix. Change only the lines required to resolve the defect. Do not refactor unrelated code in the same commit. If touching
context/sensitivity.py, apply extra scrutiny per.github/instructions/sensitivity.instructions.md. Success: fix is self-contained. -
Verify the previously-failing test now passes.
make testSuccess: the new test passes; no previously-passing test regresses.
-
Update
CHANGELOG.md. Add a concise entry under## [Unreleased]. Success: entry is present. -
Run
make ciand verify all checks pass.make ciSuccess: all targets (
fmt lint type test example demo) exit 0.
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 · 48 lines · 13 tokens per session scan A 4791547f08a3
fix-bug is a command published in the GitHub repository dgenio/contextweaver (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 13 tokens to every session and 443 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 2026-09-08.
Other commands, from other repositories
python-scaffold
Generate a fresh project skeleton, tests and lint config included. TRIGGER WHEN: the user asks to start a new Python project, bootstrap FastAPI/Django/CLI/library structure, or set up uv+pytest+ruff from scratch. DO NOT TRIGGER WHEN: adding to an existing project (use python-engineer).
build-fix
Systematically investigate and fix build errors, TypeScript errors, or test failures with minimal diffs.
fix-test
Auto-diagnose and fix failing tests — identifies root causes and applies fixes.
verify
You are invoking the verify skill - comprehensive verification following Boris Cherny's pattern.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
fix-bug
Fix a bug using the knowledge layer — reproduce first, failing regression test, root cause, surgical fix, review and ledger entry after.