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 skills add UnboundCompute/security-agent-skills --skill auditing-api-key-and-token-lifecyclegit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/auditing-api-key-and-token-lifecycle)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-api-key-and-token-lifecycle"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-api-key-and-token-lifecycle/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/unboundcompute/security-agent-skills/auditing-api-key-and-token-lifecycle"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-api-key-and-token-lifecycle.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 | $0.00202 | $0.02308 |
| Opus 5.5 | $0.00081 | $0.00923 |
| Sonnet 5.5 | $0.00040 | $0.00462 |
| Haiku 4.5 | $0.00020 | $0.00231 |
Grade A, and why
auditing-api-key-and-token-lifecycle 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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing API key and token lifecycle: a key is a standing credential, so bound it and be able to kill it
An API key or long-lived access token is a bearer credential: whoever holds it is the caller, with no second factor and often no user behind it. That makes the whole security of the key a question of its lifecycle, how narrowly it is scoped, whether it expires, whether you can actually revoke it, and where it might leak, because the moment one of those is loose, a single leaked string becomes standing access. A key issued with broader scope than its caller needs means a leak grants far more than the one function it was for. A key with no expiry stays valid forever, so a credential stolen once works until someone notices, which is often never. A revocation path that does not truly stop the key, a rotation that leaves the old key live, a disable that a cache ignores, means a compromised credential keeps authenticating after you believed you killed it. A key that leaks into logs, URLs, client-side code, or error messages and is never rotated is a published password. And a token whose scope or audience is not enforced on use works against endpoints it was never issued for. The audit follows each key from issuance to revocation and checks it is minimally scoped, expiring, truly revocable, and enforced on use. You audit this by holding a key and testing what it can reach, how long it lasts, and whether you can stop it.
When to use
- A service issues API keys or long-lived access tokens that authenticate programmatic callers.
- Keys may be issued with broad scope, no expiry, or without a working revocation path.
- A key may leak into logs, URLs, or client code, or a token's scope or audience may not be enforced on use.
Scope check
Test key and token lifecycle only against services and credentials you own or are authorized to assess, with test keys. Issuing, exercising, and revoking keys changes real access state, so use test credentials and never use, rotate, or revoke a key that is not yours. If you can't name the authorization, stop.
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.
- 1mo ago First seen · 141 lines · 202 tokens per session scan A f9d97b85abff
auditing-api-key-and-token-lifecycle is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 2,308 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.