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 dikamilo/dx-workflow --skill dx-review-triagegit clone --depth 1 https://github.com/dikamilo/dx-workflowWrote 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/dikamilo/dx-workflow/dx-review-triage)<a href="https://agentmods.dev/skills/dikamilo/dx-workflow/dx-review-triage"><img src="https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-review-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/dikamilo/dx-workflow/dx-review-triage"><img src="https://agentmods.dev/badge/skills/dikamilo/dx-workflow/dx-review-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 | $0.00024 | $0.01036 |
| Opus 5 | $0.00012 | $0.00518 |
| Sonnet 5 | $0.00005 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
dx-review-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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dx-review-triage
Turn a review report's findings into decisions — and, when you say so, into edits. dx-plan-review and dx-impl-review only analyze and report; this is the one place that acts on a finding, editing plan.md or the code it reviewed, one finding at a time, only on your confirmation. That split keeps both review gates pure: a reviewer that never fixes what it checks doesn't need to graduate into a tool-restricted agent.
Guard. Resolve <change-id> under context/changes/. reviews/ must contain plan-review.md or impl-review.md — if the directory is missing or empty, point at /dx-plan-review or /dx-impl-review instead. If the path is under context/archive/, refuse: archived work is done.
Load first
The review-report reference (invoke dx-references with review-report) — the finding-ID/Resolution schema, the resume rule, and the file conventions this skill reads and writes.
1 — Resolve which report
Each type has exactly one file — reviews/plan-review.md or reviews/impl-review.md — always the current review, since re-running dx-plan-review/dx-impl-review overwrites rather than dating a new file. A second argument names the type (plan or impl) directly. No argument: exactly one file present → use it; both present → ask which, since a plan-review and an impl-review can each carry open findings on the same change at once.
2 — Load what the fix touches
- plan-review →
plan.mdin full — this is what gets edited. - impl-review → the same diff scope
dx-impl-reviewused to review:git log/git difffor the commits that landed this change's phases, plus the specific files each pending finding names. Don't reload files findings you're skipping don't touch.
3 — Walk findings in order
Resume per the review-report reference: the first finding with Resolution: PENDING, document order. For each, show its title, location, detail, and suggested fix, then ask:
- Fix now — apply the suggested fix (or a variant you propose); show the before/after edit first, apply on confirmation.
- Fix differently — ask what they'd prefer instead, apply that.
- Skip — leave it for now, move on.
- Accept risk — leave it, record the one-line reason.
- Record as lesson — hand the finding's title and detail to
/dx-lesson's entry shape and tell the user to confirm there. Never append tofoundation/lessons.mdyourself — that file has exactly one writer.
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.
- 10d ago First seen · 57 lines · 24 tokens per session scan A 03d617f7fe04
dx-review-triage is a skill published in the GitHub repository dikamilo/dx-workflow (5 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,036 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".