Borrowing it
Nothing to install: this file belongs to nikicat/secrets-dispatcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nikicat/secrets-dispatcher/master/.claude/skills/secrets-rule/SKILL.mdgit clone --depth 1 https://github.com/nikicat/secrets-dispatcherWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nikicat/secrets-dispatcher/secrets-rule)<a href="https://agentmods.dev/skills/nikicat/secrets-dispatcher/secrets-rule"><img src="https://agentmods.dev/badge/skills/nikicat/secrets-dispatcher/secrets-rule/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nikicat/secrets-dispatcher/secrets-rule"><img src="https://agentmods.dev/badge/skills/nikicat/secrets-dispatcher/secrets-rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00103 | $0.01342 |
| Opus 5 | $0.00051 | $0.00671 |
| Sonnet 5 | $0.00021 | $0.00268 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
secrets-rule 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 9d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secrets-dispatcher Trust Rule Management
Create or modify trust rules based on the user's request. The user may provide:
- A free-text description: "block evolution from accessing secrets"
- A request ID prefix from history: "b260def"
- A vague concern: "something is accessing my keyring"
Step 1: Understand the Request
Parse $ARGUMENTS (or the user's message if auto-triggered). Determine:
- Intent: block (deny), allow (approve), ignore, or investigate?
- Target: which application/process?
- Scope: all request types, or specific ones (search, get_secret, write, delete, unlock)?
If the intent is unclear, ask ONE focused question using AskUserQuestion. Don't ask about things you can resolve from history/logs.
Step 2: Gather Evidence
Run these in parallel to identify the exact process details:
In-memory history (most useful — has full process chain with exe paths):
secrets-dispatcher history -json
If a request ID prefix was given, filter to it:
secrets-dispatcher history -json | jq '.[] | select(.request.id | startswith("PREFIX"))'
Otherwise, search for entries matching the user's description — look at process names, exe paths, search_attributes, unit names.
Journald logs for the current session (shows request flow, denials, errors):
journalctl --user -u secrets-dispatcher.service --since today --no-pager | tail -200
From the evidence, extract:
sender_info.process_chain[].exe— full executable path (preferred for rules)sender_info.process_chain[].name— comm name (CAUTION: truncated to 15 chars by Linux)sender_info.unit_name— systemd unit if applicablerequest.type— what request types the process makesrequest.search_attributes— search patterns usedrequest.items[].attributes— secret attributes accessed
Step 3: Present Findings
Show the user a brief summary of what you found:
- The process exe path and chain
- What request types it made and how often
- What secrets/attributes it accessed
- Any existing rules that already match or partially overlap
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.
- 9d ago First seen · 131 lines · 103 tokens per session scan A 902230e652d3
secrets-rule is a skill published in the GitHub repository nikicat/secrets-dispatcher (11 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,342 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
least-privilege-access-design
Analyze a system's access patterns and design least-privilege controls: classify data and APIs by risk, select the narrowest API surface for each operation, define authorization policies with multi-party approval for sensitive actions, establish emergency access override procedures, and optionally introduce a…
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
hugging-face-dataset-creator
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.
write-unit-tests
Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.
json-transform
Apply a jq-style filter to transform a JSON payload.