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 navapbc/digital-service-orchestra --skill skill-refactorgit clone --depth 1 https://github.com/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/skill-refactor)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/skill-refactor"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/skill-refactor/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/navapbc/digital-service-orchestra/skill-refactor"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/skill-refactor.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 | $0.00083 | $0.08742 |
| Opus 5 | $0.00042 | $0.04371 |
| Sonnet 5 | $0.00017 | $0.01748 |
| Haiku 4.5 | $0.00008 | $0.00874 |
Grade B, and why
skill-refactor scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rln "${s}" plugins/dso/ .claude/ tests/ docs/ 2>/dev/null | grep -v "^plugins/dso/scripts/${s%.sh}\.sh$" How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Refactor
End-to-end token-efficiency and reliability pass on a DSO skill: review → approved plan → code/doc/test changes → ticket reconciliation → tessl review → committed result.
When to use
User signals: "review the X skill", "audit X", "can we optimize X?", "clean up X", "X is bloated", "X isn't reliable", or any request that implies critiquing a specific skill file and improving it.
Inputs
- Skill name (bare, no
dso:prefix) — e.g.,architect-foundation,brainstorm. - The skill's SKILL.md at
plugins/dso/skills/<name>/SKILL.md. - Any co-located phase files under
plugins/dso/skills/<name>/phases/or equivalent.
Workflow
The workflow is nine sequential phases. Do not skip. Phases A and B are synchronous with the user; Phases C–I execute autonomously once the plan is approved.
PA Critical review → present findings
PB Remediation plan → await explicit approval
PC Script relocation → move skill-scoped scripts to shared sub-dir
PD Reference updates → skill body, tests, docs
PE Change-detector test sweep → remove prose-grepping tests
PF Ticket reconciliation → comment on open tickets affected
PG Renumbering → renumber phases (A,B,C…) and steps (1,2,3…); update cross-skill refs
PH Tessl skill review → run tessl skill review; act on valid+actionable findings
PI Commit → via COMMIT-WORKFLOW.md; surface review findings
White elephants: phrasings to remove
A white elephant in a skill file is a phrasing that is intended to enforce a rule but instead creates the very temptation it forbids. The phrase names a bypass shape (cost-pressure, urgency-pressure, perceptual judgment) and then tells the agent to ignore it. The naming makes the bypass salient. White elephants are the symmetric counterpart to the "Hard gates: compress, do not remove" rule below: hard gates are load-bearing enforcement that must be preserved (compress only); white elephants are bypass-narration that should be removed entirely (the rule's positive form already does the enforcement work).
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.
- 12d ago First seen · 457 lines · 83 tokens per session scan B eb9524be5141
skill-refactor is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 8,742 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…