Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-doctor)<a href="https://agentmods.dev/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-doctor"><img src="https://agentmods.dev/badge/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-doctor/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/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-doctor"><img src="https://agentmods.dev/badge/skills/juancolilla/agentic-agnostic-workflow-environment/agentic-environment-doctor.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 | $0.00196 | $0.03239 |
| Opus 5 | $0.00098 | $0.01620 |
| Sonnet 5 | $0.00039 | $0.00648 |
| Haiku 4.5 | $0.00020 | $0.00324 |
Grade A, and why
agentic-environment-doctor 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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Environment Doctor
Audits and repairs an AGENTS.md-based AI workflow after months of drift. Inventories every config and skill file, clusters rules by intent, detects the well-known drift symptoms, and proposes a reconciliation diff that the user approves before any destructive change.
When to use this skill
The user has an existing setup and complains:
- "My agents are ignoring rules I know are written somewhere."
- "I have three CLAUDE.md files and one of them contradicts the others."
- "My skills are duplicated across
~/.claude/skills/and project skills." - "I want to migrate from Claude-only to AGENTS.md without losing what I've written."
- "The
knowledge/articles keep going stale; nobody updateslast_verified." - "Where is X configured?" — they don't know themselves anymore.
If they want to start from scratch, use the sibling skill
agentic-environment-bootstrap. This skill is for fixing what already exists.
Mental model
Drift in an AI workflow shows up in five places. The doctor checks all five in order; each step is read-only until the user approves a fix.
| # | Symptom | Detector |
|---|---|---|
| 1 | Truth fragmented across multiple files | scripts/inventory.sh |
| 2 | Adapters that are no longer adapters (CLAUDE.md > 3 lines) | scripts/audit.py |
| 3 | Skills bloated, duplicated, or undiscoverable | scripts/audit.py |
| 4 | DESIGN.md / ARCHITECTURE.md degraded into per-screen / dead | scripts/audit.py |
| 5 | Live library articles stale (code moved, articles didn't) | scripts/knowledge-staleness.py |
| 6 | Tier leakage / budget overflow / stale compiled adapters | scripts/harness-audit.sh |
| 7 | Agent health: memory over cap, journal unconsolidated, dead skill refs, stale compiled agents | scripts/harness-audit.sh |
The full taxonomy of symptoms and what each one means is in
references/drift-symptoms.md. Read that file before judging a finding —
some symptoms are noisy on their own and only matter in combination.
What ships with it
8 files 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.
- references/drift-symptoms.md 11 KB
- references/invariants-pattern.md 4.5 KB
- references/memory-consolidation.md 2.3 KB
- references/reconciliation-playbook.md 8.6 KB
- scripts/audit.py 16 KB runs code
- scripts/harness-audit.sh 4.5 KB runs code
- scripts/inventory.sh 8.8 KB runs code
- scripts/knowledge-staleness.py 6.5 KB runs code
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.
- 10d ago First seen · 272 lines · 196 tokens per session scan A ddb7d4502e68
agentic-environment-doctor is a skill published in the GitHub repository JuanColilla/Agentic-Agnostic-Workflow-Environment (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 196 tokens to every session and 3,239 once invoked, about $0.0010 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.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…