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 jscraik/Agent-Skills --skill code-fixes-triagegit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/code-fixes-triage)<a href="https://agentmods.dev/skills/jscraik/agent-skills/code-fixes-triage"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/code-fixes-triage/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/jscraik/agent-skills/code-fixes-triage"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/code-fixes-triage.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 | $0.00064 | $0.01364 |
| Opus 5.5 | $0.00026 | $0.00546 |
| Sonnet 5.5 | $0.00013 | $0.00273 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
code-fixes-triage 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Fixes Triage
Convert noisy review and CI signals into a small action queue before starting any fix lane.
Philosophy
The useful unit is not a digest. The useful unit is a short queue that says what can move now, what only needs watching, what is informational, and what is blocked until a source of truth is refreshed.
When To Use
- Jamie points to Slack '#code-fixes', CodeRabbit notifications, Codex Review output, CI status drift, or review-noise digests.
- The request is to decide what needs attention across repos or PRs.
- A signal may lead to 'pr-green-sweep', 'autofix', 'testing', 'release-notes', or a repo-specific fix, but the first job is classification.
Inputs
- Signal source and time window, defaulting to the last 24 hours for '#code-fixes'.
- Target repos or PRs when provided.
- Available live source-of-truth tools: GitHub, CI, CodeRabbit, Linear, local repo checkout, and repo validation commands.
See 'references/contract.yaml' for the compact machine-readable contract and 'references/evals.yaml' for routing checks.
Workflow
- Gather only the relevant signal text and group it by repository and PR.
- Treat Slack and bot messages as signal surfaces, not delivery truth.
- For each item, refresh the live state that matters: GitHub PR, latest head SHA, required checks, review threads, tracker state, local branch or worktree, and relevant validation output.
- Classify each item as 'fix_now', 'monitor', 'informational', or 'blocked'.
- Name the owner lane: 'pr-green-sweep', 'autofix', 'testing', 'release-notes', 'technical-writer', repo-specific implementation, or no action.
- Promote repeated noise into the durable destination it implies: guardrail, test, docs contract, skill behavior, eval fixture, or tracker issue.
- Stop before implementing fixes unless the user asked for follow-through or the routing skill owns execution.
Outputs
schema_version: 1
mode: code_fixes_triage
window: <time window inspected>
sources: [<slack|github|coderabbit|ci|linear|local>]
action_queue:
fix_now:
- repo: <owner/repo or local path>
pr: <number-or-null>
signal: <short signal>
live_truth: <what was refreshed>
next_lane: <skill-or-agent>
blocker: null
monitor: []
informational: []
blocked: []
source_of_truth_gaps: []
durable_followups: []
validation: []
What ships with it
4 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.
- 1mo ago First seen · 121 lines · 64 tokens per session scan A 2a004656b70f
code-fixes-triage is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,364 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.
x-fix
A bug-fixing skill with separate paths for directly reported bugs, correctness-review findings, and failed verification or quality-gate reports. It records completed fixes and their validation in project reports.
do-it-audit
Use when the user explicitly requests a deep repository or scoped audit; not for ordinary diff review.
x-audit-perf
A manually triggered review of a whole software project’s performance. It looks for code and system patterns that may make programs slower or use more resources.
dpf-blast-radius
Use before shipping a DPF change to find what it breaks elsewhere — a refactor, renamed field, contract/schema/enum edit, shared helper, or a diff you do not trust.