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/fmflurry/settings-opencode/skill-authoringnpx skills add fmflurry/settings-opencode --skill skill-authoringgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWhat 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 | $0.00089 | $0.01287 |
| Opus 5 | $0.00044 | $0.00643 |
| Sonnet 5 | $0.00018 | $0.00257 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade B, and why
skill-authoring 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 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Avoid overlapping triggers with existing skills (check `/ls .claude/skills/*/SKILL.md`). How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring & Maintenance
Skills encode specialized knowledge for Claude Code's / command system. This guide ensures they stay modular, maintainable, and fast to load.
Progressive Disclosure — 3 Levels
Level 1: Frontmatter description (always loaded)
- Max 100 words. State WHEN to trigger, not how.
- Include concrete trigger phrases ("When creating…", "Use when…", "Ask when…").
- Avoid overlapping triggers with existing skills (check
/ls .claude/skills/*/SKILL.md). - Bad: "Scaffolds .NET architecture patterns." Good: "Use when creating a new bounded context or refactoring toward DDD + CQRS."
Level 2: SKILL.md body (loaded on trigger)
- Hard max 500 lines. Target < 350.
- Include only info needed on every activation: overview, core concepts, mandatory rules, quick-start checklist.
- Section structure: When to use, core concepts, required conventions, checklist.
- Wiki-link to reference files for recipes, templates, detailed examples:
[reference-name.md](reference-name.md)or[[reference-name]].
Level 3: Reference files (loaded on demand only)
- Live in the skill's directory:
skill-name/reference.md,skill-name/templates.md, etc. - Contain: recipes, SQL boilerplate, full code examples, edge cases, detailed checklists, FAQ.
- Linked from body via
[name](file.md)or[[wiki-link]]. - One skill may link to another's reference file (shared doctrine, not duplicated).
Add vs Split Heuristic
| Info Type | Body | Reference | Another Skill |
|---|---|---|---|
| Core concept, rule on every use | Yes | — | — |
| "Only if…" workflow, edge case | — | Yes | — |
| Shared by several skills (DRY) | — | — | Yes, link to it |
Example: dotnet-cop and security-review both link to dotnet-clean-architecture/postgres-schema-per-context.md instead of copying the RLS doctrine.
Description Quality (Trigger Activation)
- Concrete triggers: "When creating…", "Use when…", "Ask when…"
- No overlaps: Skill A triggers on
"new feature + tests", Skill B on"refactor + tests"→ collision. Disambiguate ("ATDD outer loop" vs "TDD inner loop"). - No content summaries in description. Bad: "Explains progressive disclosure, add-vs-split, and anti-patterns." Good: "Use when writing a skill or asking if a skill is too large."
- Test: Would a user know when to invoke
/based only on the description?
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 · 96 lines · 89 tokens per session scan B ebdfa86b97f2
skill-authoring is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed 20d ago), licensed MIT. It adds 89 tokens to every session and 1,287 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…