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/crypticswarm/swarmforge/skill-writernpx skills add CrypticSwarm/Swarmforge --skill skill-writergit clone --depth 1 https://github.com/CrypticSwarm/SwarmforgeWhat 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 | $0.00047 | $0.01755 |
| Opus 5 | $0.00023 | $0.00877 |
| Sonnet 5 | $0.00009 | $0.00351 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
skill-writer 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Writer
Use this guide whenever you need to create, revise, or maintain a skill (a modular package that expands the agent with domain knowledge, workflows, or tooling). Skills act like onboarding kits: they teach the agent how to approach a recurring problem reliably.
Skills at a Glance
- Specialized workflows – codified, repeatable procedures for fragile or multi-step tasks.
- Tool integrations – instructions for working with specific APIs, formats, or scripts.
- Domain expertise – company, product, or dataset knowledge that the base model lacks.
- Bundled resources – scripts, references, and assets reused across sessions.
Keep every skill lean. Assume the agent already knows general programming, writing, and reasoning; only include content that is unique to the domain or workflow.
Core Principles
-
Implicit vs explicit activation.
- Skills may be activated explicitly via the
skilltool or implicitly via strong trigger language. - For fragile or critical workflows, assume explicit activation.
- For common, narrow tasks (e.g. commit messages), optimize for implicit activation through the description.
- Skills may be activated explicitly via the
-
Protect the context window. Every token in a skill competes with live conversation history. Prefer short, actionable guidance over essays. Use tables, bullets, or concise examples instead of prose.
-
Match specificity to task fragility.
- High freedom → text instructions and heuristics (open problem spaces).
- Medium freedom → pseudocode or parameterized scripts (preferred patterns, but variations allowed).
- Low freedom → exact scripts/commands (fragile operations, compliance, or prod changes).
-
Progressive disclosure. Organize content so only the necessary layer loads:
- YAML frontmatter (
name,description) – always visible, describes when to trigger. SKILL.mdbody – core workflows (<500 lines).- Optional
scripts/,references/,assets/– loaded only when invoked.
- YAML frontmatter (
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.
- 2d ago First seen · 117 lines · 47 tokens per session scan A 3a6513031c50
skill-writer is a skill published in the GitHub repository CrypticSwarm/Swarmforge (2 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 1,755 once invoked, about $0.0002 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…