Borrowing it
Nothing to install: this file belongs to GSA-TTS/agentic-coding-playbook. 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/GSA-TTS/agentic-coding-playbook/main/.agents/skills/agent-permissions/SKILL.mdgit clone --depth 1 https://github.com/GSA-TTS/agentic-coding-playbookWrote 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/gsa-tts/agentic-coding-playbook/agent-permissions)<a href="https://agentmods.dev/skills/gsa-tts/agentic-coding-playbook/agent-permissions"><img src="https://agentmods.dev/badge/skills/gsa-tts/agentic-coding-playbook/agent-permissions.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02004 |
| Opus 5 | $0.00012 | $0.01002 |
| Sonnet 5 | $0.00005 | $0.00401 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
agent-permissions 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 6d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Agent Environment Doctor
Detect what credentials and tools an AI coding agent has access to, diagnose gaps against the project plan, and output actionable fix commands for each missing item.
When to Use
- First thing after cloning a repo — before the agent tries to push, deploy, or call APIs
- Agent reports "permission denied" or "authentication failed"
- Onboarding a new developer or setting up a new environment
- Running the agent in a sandboxed environment (Codespace, container, CI runner)
- After rotating credentials to verify everything still works
Core Principles
Detect, don't create. A sandboxed agent cannot create tokens or access browser UIs. This skill checks what's available and tells the human exactly what to fix.
Never log secret values. Check env var names and CLI auth status only. Never print, log, or transmit credential values.
Least privilege. Every credential gets the minimum scope needed for its job.
Quick Start
# Run the environment doctor
make doctor
# Machine-readable JSON output
make doctor-json
# With custom project plan path
PYTHONPATH=scripts python3 -m playbook_validator doctor --plan path/to/PROJECT_PLAN.md
How It Works
The doctor runs three phases:
Phase 1: Detect
Scans the environment for available tools and credentials:
| Check | Method | What It Proves |
|---|---|---|
| Git | command -v git |
Version control available |
| Git remote | git remote get-url origin |
Platform identified (GitHub/GitLab) |
| GitHub CLI | gh auth status |
Can create PRs, issues, manage repo |
| GITHUB_TOKEN | env var presence | API access for automation |
| cloud.gov CLI | cf target |
Can deploy applications |
| GitLab token | GITLAB_TOKEN env var | Can push to GitLab instance |
| AI API keys | ANTHROPIC_API_KEY, OPENAI_API_KEY, etc. | Agent has LLM access |
| .gitignore | grep for .env pattern |
Secrets won't be committed |
Phase 2: Diagnose
Compares detected capabilities against PROJECT_PLAN.md requirements:
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.
- 6d ago First seen · 265 lines · 24 tokens per session scan A 051189b0a898
agent-permissions is a skill published in the GitHub repository GSA-TTS/agentic-coding-playbook (23 stars, last pushed 4d ago), licensed CC0-1.0. It adds 24 tokens to every session and 2,004 once invoked, about $0.0001 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
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…