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/fixnpx skills add OutlineDriven/odin-gemini-cli-extension --skill fixgit 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/fix)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/fix"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/fix.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 | $0.00108 | $0.01532 |
| Opus 5 | $0.00054 | $0.00766 |
| Sonnet 5 | $0.00022 | $0.00306 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
fix 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 fix — 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix
Failure-driven iterative repair. Detect → Prioritize → Fix ONE thing → Commit → Verify → Keep/Revert → Repeat.
When to Apply / NOT
Apply: user says "fix", "make it pass", "apply findings"; input is a verifier failure, findings file, or bug description.
NOT apply:
- CI/PR workflows with no local context → use
gh-fix-ci - PR review comments → use
gh-address-comments - Merge conflicts
- Analysis-only tasks → use
resolveordebug - Planned change without a failure driver → use
proceed
Detected Mode Acknowledgement [LOAD-BEARING]
First output line before ANY edit:
detected: <mode> — target=TARGET guard=GUARD scope=SCOPE cap=20
Mode values: gh-route, findings, verifier-failure, bug-spec. Full classifier: references/classifier.md.
Input Classifier
First-match wins. Full detail: references/classifier.md.
| Priority | Mode | Minimum condition |
|---|---|---|
| 1 | gh-route |
GH-flavored input + open PR + gh auth status clean |
| 2 | findings |
Path to */findings.md, */review/*.md, or structured findings text |
| 3 | verifier-failure |
Raw verifier stdout (FAILED, error TS, --- FAIL, etc.) |
| 4 | bug-spec |
Natural-language description — catch-all fallback |
Auto-Detect Gate
Auto-infer: target verifier, scope glob, guard command, iteration cap (default 20).
Trigger AskUserQuestion (single-select per axis, NEVER multiSelect) when:
MIXED_MODE: findings artifact AND verifier-failure output both presentGH_PARTIAL: GH-flavored input but no open PR, orgh auth statusfailsLANG_UNKNOWN: verifier-failure detected but verifier undetectableSCOPE_AMBIGUOUS: bug-spec with no module, file, or component reference
Iterative Loop
Full spec: references/loop.md. Key rules:
- One fix per iteration. Apply fix → stage checkpoint commit → run verifiers → KEEP on green, revert with
git revert HEAD --no-editon red. A commit is kept only when the guard passes. - Decide matrix:
delta > 0+ guard ok → KEEPdelta > 0+ guard fail → REWORK (max 2 reworks per item; 4th attempt → SKIP)delta ≤ 0→ DISCARD — revert immediately- 3 total skips → HALT with summary
- Revert: always
git revert HEAD --no-edit. Neverreset --hard. - Cap: 20 iterations default. Print progress every 5 iterations.
- Refuse loop on protected branches (
main,master,release/*). - Override:
iterations: Nor--iterations Nin invocation.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 132 lines · 108 tokens per session scan A a16d270343c3
fix 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 108 tokens to every session and 1,532 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to fix, 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).