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/cintia09/codenook/dispatch-auditnpx skills add cintia09/CodeNook --skill dispatch-auditgit clone --depth 1 https://github.com/cintia09/CodeNookWhat 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 | $0.00000 | $0.00562 |
| Opus 5 | $0.00000 | $0.00281 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
dispatch-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dispatch-audit (builtin skill)
Role
Redacted append-only logger for sub-agent dispatches. Every time the main session (or orchestrator-tick) dispatches a helper/worker agent, it calls this skill to log a one-line audit record AND enforce the 500-byte payload hard limit (architecture §3.1.7 / v6 decision #T-3). The limit is measured in UTF-8 bytes (CJK-safe).
CLI
emit.sh --role <name> --payload <json-string> [--workspace <dir>]
--rolee.g.planner,coder,reviewer— the downstream role.--payloadraw JSON string; must parse and be ≤ 500 bytes (UTF-8) total.--workspacedefaults to$CODENOOK_WORKSPACE; if unset, upward search for a directory containing.codenook/.
Exit codes
| code | meaning |
|---|---|
| 0 | logged |
| 1 | payload > 500 bytes, or not valid JSON |
| 2 | usage error / workspace not resolvable |
Log line shape
Appended to <ws>/.codenook/history/dispatch.jsonl:
{
"ts": "2026-04-18T12:34:56Z",
"role": "planner",
"payload_size": 187,
"payload_sha256": "…",
"payload_preview": "… first 80 chars …"
}
Note: full payload is never written — only sha256 + an 80-char preview. Privacy by construction.
Redaction
Before the 80-char preview is sliced, the payload is run through a
best-effort secret scrubber that masks common high-confidence patterns
(OpenAI sk- / sk-proj-, Anthropic sk-ant- / sk-ant-api03-, AWS
AKIA…, GitHub ghp_ / gho_ / github_pat_, and PEM private-key
headers) with the literal string [REDACTED]. This is best-effort
defence-in-depth, not a substitute for keeping secrets out of payloads
(callers SHOULD pass ${env:NAME} placeholders, not resolved values).
M1 notes
- Single-line append; no explicit flock (line sizes are far below
PIPE_BUFso concurrentwrite()calls stay line-atomic on POSIX). .codenook/history/auto-created when missing.
What ships with it
2 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.
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 · 62 lines · 0 tokens per session scan A 9c7e806a63c0
dispatch-audit is a skill published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 562 tokens. 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…