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/xrensiu/claude-code-forge/dos-extractnpx skills add XRenSiu/claude-code-forge --skill dos-extractgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/dos-extract)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/dos-extract"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/dos-extract.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 | $0.00318 | $0.02489 |
| Opus 5 | $0.00159 | $0.01244 |
| Sonnet 5 | $0.00064 | $0.00498 |
| Haiku 4.5 | $0.00032 | $0.00249 |
Grade A, and why
dos-extract 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 3d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dos-extract
Reverse-engineer a Design Ontology Spec from a repository. The product is two files:
dos.yaml (the 12-section ontology) + decisions.md (why Topic, not TopicNode).
This skill describes what a DOS is, the judgments that separate a real ontology from a
scan dump, the primitive that does the mechanical scanning, the human seam, and the exit
that certifies the result. It prescribes no step order — the engine sequences the work;
what follows are the gaps and the gates.
The gap (why a scan is not an ontology)
A composite of three atoms: Knowledge (what a DOS is — the 12-section format, the code-vs-docs signal priority), Capability (the mechanical noun/verb scan — a primitive the engine otherwise mis-improvises), Judgment (the four classification calls below).
The load-bearing reason this is not free:
Code contains the current implementation choices, not the ontology that should exist. A naive "scan code → emit objects" pass freezes mistakes into the contract: a
CommentCardReact component becomes aCommentCardobject — wrong twice (it is UI, andCardis presentation, not domain).
Deletion test: remove this skill and ask the engine to "extract a DOS from this repo." It
greps nouns and emits a polluted ontology — UI elements and *Repository/*Service names
promoted to objects, no ≤7 discipline, code vocabulary winning over the team's language.
The gap is the semantic judgment, plus the knowledge of what a clean DOS looks like.
The world
- A DOS is a YAML contract in a fixed 12-section shape (
assets/dos_template.yaml): meta, scope, objects, relationships, rules, composition, behaviors, bounded_contexts, agent_guidelines, anti_patterns, open_questions, evolution_log. It is the shared language between humans and AI agents — code converges to it, not it to code. - Two signal sources, divergence is signal. Code shows what was built; docs show
what the team talks about. When they agree, confidence is high. When they diverge (docs
say
Topic, code saysNode), that divergence is itself evidence — and for ontology questions docs generally outrank code (code drifts under deadline; docs reflect intent). Full priority rules:references/methodology.md(code-vs-docs signal priority). - Output is two files.
dos.yaml(the ontology) +decisions.md(the audit trail — every non-trivial judgment traceable to one of the four by name).
What ships with it
10 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.
- assets/decisions_template.md 10 KB
- assets/docs_extraction_prompt.md 7.8 KB
- assets/dos_template.yaml 14 KB
- eval/gate.json 2.7 KB
- eval/report.md 2.4 KB
- references/anti_patterns.md 9.8 KB
- references/judgments.md 12 KB
- references/methodology.md 13 KB
- scripts/inventory.py 15 KB runs code
- scripts/verify_dos.py 4.7 KB runs code
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.
- 3d ago First seen · 170 lines · 318 tokens per session scan A ea80a70a3154
dos-extract is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 318 tokens to every session and 2,489 once invoked, about $0.0016 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…