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/trustmybot/plugin/tmb_docs-conventionsnpx skills add trustmybot/plugin --skill tmb_docs-conventionsgit clone --depth 1 https://github.com/trustmybot/pluginWhat 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 | $0.00056 | $0.00437 |
| Opus 5 | $0.00028 | $0.00218 |
| Sonnet 5 | $0.00011 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
tmb_docs-conventions 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.
What it actually says
Docs Conventions — Editing Discipline
When editing prompt files or user-visible docs, follow these rules.
Docs-update expectation
When functionality changes, the same PR updates the user-visible docs that describe it. The PR-reviewer flags missing doc updates at the push gate. This is a judgment call (what counts as user-visible?).
When docs and code disagree
If a doc you're updating contradicts the code, halt and surface it — pick the side that matches the intended behaviour, update the other, and flag the discrepancy first. Ground in the code itself (and the world model), not in the prose that describes it.
Editing prompt files (agents, skills, CLAUDE.md, workflow markdown)
- Delete before you add. A shorter prompt is usually clearer. Prefer removal over addition when both achieve the goal.
- Preserve operational meaning. Copy constraints, prohibitions, and weighted examples verbatim — e.g. a
LOAD-BEARING-SAFETYcomment, a "HALT" rule, or an exact wire-format string — unless the request explicitly changes them. - Match tone and structure. Edits blend into the target file; they don't impose a different style.
- Stay in scope. Correct what was asked; don't opportunistically rewrite adjacent content.
- Update referenced paths. When you rename or move a file the prompt cites, grep for every reference and update it in the same commit.
- Diff, don't rewrite. Produce edits as a focused diff unless a full rewrite was explicitly requested.
Escalation
- Ambiguous rewrite request → ask specific questions, don't guess.
- Target file has internal contradictions → quote them, flag to the caller.
- Change would break files that reference this one → flag the ripple before proceeding.
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 · 32 lines · 56 tokens per session scan A c00a91b2f5fc
tmb_docs-conventions is a skill published in the GitHub repository trustmybot/plugin (6 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 437 once invoked, about $0.0003 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
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…