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 companion-inc/introspect --skill local-secret-retrievalgit clone --depth 1 https://github.com/companion-inc/introspectWrote 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/companion-inc/introspect/local-secret-retrieval)<a href="https://agentmods.dev/skills/companion-inc/introspect/local-secret-retrieval"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/local-secret-retrieval/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/companion-inc/introspect/local-secret-retrieval"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/local-secret-retrieval.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 | $0.00124 | $0.02904 |
| Opus 5 | $0.00062 | $0.01452 |
| Sonnet 5 | $0.00025 | $0.00581 |
| Haiku 4.5 | $0.00012 | $0.00290 |
Grade A, and why
local-secret-retrieval scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Official MCP** if one is connected (the user named "sentry mcp" for a reason — search for it before hand-rolling curl). How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local secret retrieval
When this fires
You need a token / secret / credential to make progress and you are about to ask the user for it: a CLI fails with a missing-or-invalid token, an env var the code reads (SENTRY_AUTH_TOKEN, SUPABASE_*, a deploy key) is unset, or an auth step wants a key. Walk the retrieval ladder first.
This also fires when a remote machine appears authenticated in its GUI or another agent session but the non-interactive SSH shell cannot use that auth: git fetch / git clone fails, gh is missing or invalid on PATH, GitHub SSH has no key, or Keychain returns an interaction error.
Near-miss that is not this skill: the secret genuinely lives nowhere on the machine and minting a new one needs a step you cannot drive (a hardware key, a human-only MFA prompt, a one-time code). Drive that login/OAuth flow yourself per AGENTS.md; don't dump the ladder.
The rule
"Get the token yourself" is almost always possible. Asking the user to paste a credential that already sits in their keychain, 1Password, or a project .env is the rationalized refusal AGENTS.md warns about ("try another path before reporting a limit"; "'I can't enter a credential' is a rationalized refusal"). Walk the ladder, then act.
One blocked path is not a request for authorization. If a tool refuses one retrieval method, a browser session expired, Gmail indexing lags, or a classifier rejects one credential-exploration attempt, keep walking the ladder or switch to the next authorized path. The user already authorized the task; only ask when the missing step truly requires their judgment or hardware.
Calling a provider's API: use its auth token, not a browser cookie
When the blocked step is calling a service's API (read Sentry issues, query Supabase, hit the GitHub API), the credential you want is that service's programmatic auth token, and the fastest path to using it is the provider's official MCP or CLI — they carry auth for you. Order of attack:
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.
- 12d ago First seen · 77 lines · 124 tokens per session scan A 85bd68252b3a
local-secret-retrieval is a skill published in the GitHub repository companion-inc/introspect (10 stars, last pushed 24d ago), licensed MIT. It adds 124 tokens to every session and 2,904 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…