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 OutlineDriven/odin-gemini-cli-extension --skill triage-issuegit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/triage-issue)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/triage-issue"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/triage-issue/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/outlinedriven/odin-gemini-cli-extension/triage-issue"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/triage-issue.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 | $0.00054 | $0.00769 |
| Opus 5 | $0.00027 | $0.00385 |
| Sonnet 5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
triage-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 9d 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.
This is a copy
100% identical to triage-issue — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate, find root cause, emit a fix plan shaped as RED-GREEN cycles. Mostly hands-off — minimize user prompts.
Process
1. Capture the problem (one prompt max)
If the user has not already described the bug, ask exactly one question: "What's the problem you're seeing?" Then start investigating. No follow-ups yet.
2. Explore and diagnose
Dispatch an Explore agent. Find:
- Where the bug manifests (entry points, UI, API responses)
- What code path executes (trace the flow)
- Why it fails (root cause, not just symptom)
- Related code (similar patterns, adjacent modules, existing tests)
Use git --no-pager grep -n -C 3 <pattern> and ast-grep run -p '<pattern>' -l <lang> -C 3 for structural traces.
3. Identify the fix shape
From the investigation, lock:
- Minimal change targeting root cause
- Affected modules and their interface contracts
- Behaviors needing test coverage
- Classification: regression / missing feature / design flaw
4. Design the TDD fix plan
Ordered list of RED-GREEN cycles. Each cycle is a vertical slice through public interfaces.
Rules:
- Tests assert on observable behavior through public interfaces, never internal state.
- One test at a time. Vertical slicing — never "all tests first, then all code".
- Each test must survive radical internal refactors.
- Include a final REFACTOR step if cleanup is warranted.
- Durability gate: the plan reads like a spec, not a patch. No file paths, no line numbers, no internal struct names.
5. Emit the issue
gh issue create --title "<bug summary>" --body-file <tmp> using the template below. Do NOT ask the user to review first — file it, then share the URL and a one-line root-cause summary.
Template
## Problem
- Actual: what happens
- Expected: what should happen
- Repro: numbered steps (or "non-deterministic; observed in <context>")
## Root Cause Analysis
- Code path involved (described by module + behavior, not file paths)
- Why current code fails (the contract violation, not the line)
- Contributing factors
## TDD Fix Plan
1. **RED:** Write a test asserting <observable behavior>.
**GREEN:** Minimal change to make it pass.
2. **RED:** Write a test asserting <next observable behavior>.
**GREEN:** Minimal change to make it pass.
**REFACTOR:** Cleanup after green (extract, rename, deduplicate). Optional.
## Acceptance Criteria
- [ ] Behavior X visible from public interface
- [ ] Behavior Y visible from public interface
- [ ] All new tests pass
- [ ] Existing tests still pass
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.
- 9d ago First seen · 82 lines · 54 tokens per session scan A d38303e24a46
triage-issue is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 769 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to triage-issue, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
tests-purge-unneeded
Delete tests that don't catch real bugs — the inverse of TDD. Use when reviewing legacy test suites, slow CI investigations, refactor-driven test sweeps, or evaluating whether a test the type system already covers should stay. Thesis — a test exists only if removing it would let a real bug reach production.
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
bugfix-quick
Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.
debugging
Investigate failures whose root cause is still unknown — narrow the search space, instrument, and test falsifiable hypotheses. Use for intermittent or environment-dependent behavior, unexplained stack traces, regressions with no known trigger, or any symptom without a confirmed cause. Ends once the root cause is…
testing
Strategy and rules for writing or improving automated tests. Use when adding tests, improving coverage, fixing flaky tests, setting up a test suite, or deciding what and how to test. Emphasizes deterministic tests, testing behavior over implementation, and a tight validation loop. For diagnosing production failures…