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 skills add YourTechBud/coding-harness-config --skill fix-buggit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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/skills/yourtechbud/coding-harness-config/fix-bug)<a href="https://agentmods.dev/skills/yourtechbud/coding-harness-config/fix-bug"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/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/skills/yourtechbud/coding-harness-config/fix-bug"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/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 | $0.00044 | $0.00662 |
| Opus 5.5 | $0.00018 | $0.00265 |
| Sonnet 5.5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Bug
Take the bug the user has described from a confirmed reproduction to a verified fix, with the user choosing which fix to make. This process guards against three failures: fixing a different bug from the one the user saw, patching the symptom when the defect calls for a structural change, and finishing without evidence that the bug is gone.
Reproduce and trace
Delegate reproduction to a subagent, giving it the observed and expected behavior and everything the user shared.
The reproducer builds an executable reproduction that fails because of the bug. It prefers the cheapest faithful route: existing tests or commands, then fixtures and mocks, and running the app only as a last resort after the user agrees. Static analysis helps decide where to look but does not count as reproduction. Mocks stay away from the suspected defect so the reproduction exercises the real faulty code and cannot fail or later pass because of the mocks.
Reproduction code is throwaway. The reproducer keeps it together in the project's gitignored scratch directory, or in its fixtures directory when that fits better, and reports:
- the single command that runs the reproduction
- the observed and expected outcomes
- the mechanical cause: the chain from input to the point where behavior goes wrong, with evidence
When the reproduction diverges from what the user described, or the bug cannot be reproduced, stop and bring that back to the user with what was reproduced or tried, the remaining hypotheses, and what information would help. Otherwise continue.
Analyze fixes
Delegate fix analysis to one subagent, giving it the reproducer's report. The analyst first establishes the structural cause: what this bug is an instance of, which layer should own the responsibility that failed, and where else the same weakness exists. It derives the class fix from that before considering the instance fix, so the quick fix does not anchor the ideal one.
- Class fix: the change that removes the whole category of bug at the layer that should own it, including re-architecture, a new ADR, or changes to existing ADRs when the fix calls for them.
- Instance fix: the smallest change that makes the reproduction pass where the symptom appears.
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.
- 12d ago First seen · 42 lines · 44 tokens per session scan A 8db8e4d663f8
fix-bug is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 662 once invoked, about $0.0002 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 2026-10-20.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.