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/nitinbhide/tcaitoolkit/agent-auditnpx skills add nitinbhide/tcaitoolkit --skill agent-auditgit clone --depth 1 https://github.com/nitinbhide/tcaitoolkitWhat 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 | $0.00060 | $0.01274 |
| Opus 5 | $0.00030 | $0.00637 |
| Sonnet 5 | $0.00012 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
agent-audit 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Audit Skill
This skill evaulates AGENTS.md file at the root of the project for following criteria. Objective is to improve the quality of results fromLLMs, reduce the number of turns in agent loop and reduce the LLM token consumptions
How to Audit the AGENTS.md file
- Audit only the repository-root
AGENTS.mdfile. - If the repository root does not contain an
AGENTS.mdfile, stop immediately and report that the audit could not run because the repository-rootAGENTS.mdis missing. - Use the "evaluation criteria" given below and check each item the list
- Treat a "first-level referenced file" as an explicit repository-relative file path written directly in the repository-root
AGENTS.md. - Check only first-level referenced paths for evaluation. Evaluate files that resolve to existing files and skip directories/folders.
- If a first-level referenced path is unresolved or invalid, record it as a warning only. Do not fail the entire audit because of unresolved or invalid referenced paths.
- Do not infer file paths, search the repository for matching filenames, or follow vague references such as "see design docs" unless a concrete file path is given.
- Stop at first-level references from
AGENTS.md. Do not recurse into files referenced by those files. - Output the report using the fixed format defined below.
Output format
Use the following sections in this exact order.
- Target
- Repository root path.
- Audited file path (must be repository-root
AGENTS.md).
- Preflight
- Repository-root
AGENTS.mdpresent: yes/no. - If no, report hard failure and stop.
- Criteria results
- Report one line per criterion.
- Allowed status values: fulfilled, not-fulfilled, not-applicable.
- Include a short rationale for each status.
- Include the evidence file paths used for evaluation.
- Reference path warnings
- List unresolved or invalid first-level referenced file paths as warnings.
- Explicitly state that these warnings do not cause audit failure.
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 · 83 lines · 60 tokens per session scan A 8d19200e703f
agent-audit is a skill published in the GitHub repository nitinbhide/tcaitoolkit (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,274 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…