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 agentmods add skills/outlinedriven/odin-gemini-cli-extension/qanpx skills add OutlineDriven/odin-gemini-cli-extension --skill qagit 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/qa)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/qa"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/qa.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00754 |
| Opus 5 | $0.00031 | $0.00377 |
| Sonnet 5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
qa 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 6d 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 qa — 0 lines 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run an interactive QA session. The user describes problems. You clarify lightly, explore the codebase in the background for domain language, and file issues that are durable and user-focused. Each issue is independent — never batch.
For Each Reported Issue
1. Listen, lightly clarify
Let the user describe the problem in their own words. Ask at most 2-3 short questions, only on:
- Expected vs actual behavior
- Steps to reproduce (if not already obvious)
- Consistent vs intermittent
Do NOT over-interview.
2. Explore in background
Dispatch an Explore agent in parallel while the user talks. Goal is NOT to find a fix — it is to:
- Learn the domain language used in that area (read
UBIQUITOUS_LANGUAGE.mdif present) - Understand what the feature is supposed to do
- Identify the user-facing behavior boundary
Context informs the issue body; the issue body itself does NOT cite files, line numbers, or internal module names.
3. Assess scope
Single issue or breakdown? Break down when fix spans multiple independent areas, separable concerns parallelize across people, or user describes multiple distinct failure modes.
4. File via gh issue create
Do NOT ask the user to review the body first — file it, share URLs.
Issue body rules:
- No file paths, no line numbers
- Use the project's domain language; never internal symbol names
- Describe behavior, not code: "the sync service fails to apply the patch", not "applyPatch() throws on line 42"
- Reproduction steps are mandatory
- 30-second readability — concise
Single-Issue Template
## What happened
Plain-language actual behavior.
## What I expected
Plain-language expected behavior.
## Steps to reproduce
1. Concrete step using domain terms
2. Concrete step
3. Concrete step (include relevant inputs/flags)
## Additional context
Observations from the user or background exploration.
Reproduction-Step Examples
Web app:
- Sign in as a Pro-tier user
- Open the export dialog from the Reports tab
- Choose CSV format and click Export
- Observe: download fails silently with no toast.
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.
- 6d ago First seen · 87 lines · 62 tokens per session scan A 1e86e62b2e52
qa 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 62 tokens to every session and 754 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 qa, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
srgn-cli
Build safe, syntax-aware srgn CLI commands for source-code search and transformation. Use for srgn commands, scoped refactors (comments/docstrings/imports/functions), multi-file rewrites with --glob, tree-sitter queries, or CI checks with --fail-any/--fail-none.
fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact…
ast-grep
Code search, analysis, and refactoring using ast-grep (sg). Use for AST-based code modifications, structural search, and linting.
qa
Conversational QA mode — user reports bugs in plain language, agent clarifies minimally, files GitHub issues that survive refactors. Trigger on "QA", "QA session", or ad-hoc bug reporting without a fixed deliverable shape. Distinct from branch-scoped and PR-scoped review.
debug
Hypothesis-driven defect isolation — stack-trace forensics, breakpoint strategy, state inspection, and root-cause confirmation via minimal repro. Use when a defect surfaces (test failure, crash, exception, wrong output, intermittent flake) and the cause is not immediately obvious from the change set.
perf-profile
Hotspot detection and performance root-cause analysis: flamegraph interpretation, allocation tracking, latency profiling, regression measurement. Use when a workload misses its latency, throughput, or memory budget; when a benchmark regresses; or before optimizing any hot path (no optimization without a profile).