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/facebook/agentic-tools/debug-access-tokennpx skills add facebook/agentic-tools --skill debug-access-tokengit clone --depth 1 https://github.com/facebook/agentic-toolsWhat 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 | $0.00094 | $0.02061 |
| Opus 5 | $0.00047 | $0.01030 |
| Sonnet 5 | $0.00019 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
debug-access-token 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Access Token
Help a developer figure out why a Meta access token is failing — without ever handling the raw token yourself.
Security first — never handle a live token
An access token is a bearer credential: whoever holds it can act as its owner. Anything pasted into this chat enters the agent's context and is transmitted to the AI provider (logs, history, retention). Treat a token like a password.
- Do NOT ask the developer to paste an access token (or an app secret) into this chat. Inspect tokens using the developer-run options below, and ask only for the resulting metadata.
- If a token was already pasted, tell the developer to revoke/rotate it (Graph API Explorer, or the app dashboard → regenerate), then continue with the metadata flow below using a fresh token.
Workflow
-
Confirm the symptom. Ask what failed:
- The error
codeandsubcode(e.g.190/463) - Which endpoint/request failed
- Which app the call was made with, and what the token is expected to do (which permissions/scopes)
- The error
-
Have the developer inspect the token themselves. Offer either option — both run in the developer's own environment and return only metadata, never routing the token through this agent:
- A. Access Token Debugger (web): open https://developers.facebook.com/tools/debug/accesstoken/, paste the token there (a Meta first-party surface, not this agent), and read the results panel.
- B.
debug_tokenGraph API via the bundled script: this skill ships a ready-to-run script,scripts/debug_token_probe.py, that reads the token and app secret from environment variables (by name — never their values) and prints only redacted metadata; the developer sets the env vars and runs it in their own shell, then brings back only the printed JSON. See the Using thedebug_tokenscript section below for how to run it and the expected output. Reference: debug_token docs. Never ask the developer to send you the token or the app secret.
What ships with it
1 file 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 · 145 lines · 94 tokens per session scan A eefffcc2d388
debug-access-token is a skill published in the GitHub repository facebook/agentic-tools (5 stars, last pushed 11d ago), licensed MIT. It adds 94 tokens to every session and 2,061 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…