check-agent-compatibility

check-agent-compatibility is a skill for Claude Code, Codex from OutlineDriven/outline-driven-development. It costs 40 tokens per session (822 once invoked), scanned A, original, Apache-2.0.

A read-only repository audit for checking whether a coding project is set up correctly for AI coding agents. It examines agent instructions, configuration files, and related startup behavior, then produces a scored report.

In plain words
What is it for?
Use it to inspect agent configuration surfaces, test configuration loading, and receive prioritized compatibility fixes.
Why use it?
It helps reveal missing, broken, or conflicting agent setup before an agent is asked to work on the repository.

Skill for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to inspect agent configuration surfaces, test configuration loading, and receive prioritized compatibility fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/outline-driven-development/check-agent-compatibility
Install

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.

Any agent
npx skills add OutlineDriven/outline-driven-development --skill check-agent-compatibility
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Claude Code, Codex.

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.

agentmods badge for check-agent-compatibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/check-agent-compatibility.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/check-agent-compatibility)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/check-agent-compatibility"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/check-agent-compatibility.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 27
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00822
Opus 5 $0.00020 $0.00411
Sonnet 5 $0.00008 $0.00164
Haiku 4.5 $0.00004 $0.00082

Measured 2d ago against content hash 92beadd8e9ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

check-agent-compatibility 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.devin/skills/check-agent-compatibility/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check agent compatibility

Contract

Field Bound contract
Trigger Full repository agent-compatibility pass, invoked explicitly by a human
Authority Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effect Chat output only; target is read-only CLI and review passes. No repository, configuration, or remote state is changed
Done A scored compatibility report with prioritized fixes and broken-down dimension results is returned

Inputs

  • Repository path to audit (must be supplied).
  • Optional scope limit (subdirectory or file glob) narrowing the pass; when omitted the whole repository is audited.

Procedure

  1. Parse scope and bind to the repository. Resolve the repository path to an absolute directory and apply the optional scope limit. Do not widen scope mid-pass. Done when: scope is bound to the repository path and optional limit.
  2. Discover agent configuration and instruction surfaces. Scan for: .claude/ directories (settings.json, commands/, hooks/), CLAUDE.md and AGENTS.md files, .cursor/ directories, plugin.json or .claude-plugin/ manifests, agents/openai.yaml skill manifests, MCP configuration files (.mcp.json, mcp.json), and any skills/*/SKILL.md trees. Done when: all agent configuration and instruction surfaces within scope are discovered.
  3. Validate syntax, schema, and dependency resolution for discovered surfaces. For each surface: parse JSON/YAML syntax, check required schema fields against the expected format, and verify that referenced files (entry points, hook scripts, skill directories) exist and resolve. Done when: every discovered surface is validated or its validation error is recorded.
  4. Run read-only agent startup and configuration loading. Attempt to load the agent configuration as the host would: parse settings, resolve hook definitions without executing them, resolve tool permissions, and load skill manifests. Registering a hook in the host runs its command, so resolve and validate hook definitions only; do not register or run them. Capture any startup errors, missing dependencies, or configuration conflicts. Do not execute any tool or mutation. Done when: startup and configuration loading is attempted, hook definitions are resolved without execution, and results are captured.
  5. Aggregate findings into a scored compatibility report. Score each of the four dimensions on a 0-100 scale:
    • Configuration validity (syntax, schema, field completeness)
    • Instruction reliability (documented instructions match observed repository behavior)
    • Startup readiness (configuration loading and tool registration succeed without mutation)
    • Dependency resolution (referenced files, entry points, and skill paths resolve) Compute the composite as the unweighted average of available dimension scores. A dimension that could not be evaluated contributes no score and does not lower the composite. Rank findings by impact on agent compatibility. Done when: the scored report with prioritized fixes is produced.

Read the full file on GitHub · 45 lines

Files

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.

Changes

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.

  1. 2d ago Changed · -17 tokens per session 92beadd8e9ec
  2. 4d ago First seen · 45 lines · 57 tokens per session scan A 11ec085578ed

Subscribe to this mod's changes

check-agent-compatibility is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 822 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

audit-project

Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".

OutlineDriven/odin-claude-plugin · 50 tokens

duet

Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.

OutlineDriven/odin-claude-plugin · 28 tokens

goal-prompt-drafting

Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.

OutlineDriven/odin-claude-plugin · 57 tokens

handoff-prompt

Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.

OutlineDriven/odin-claude-plugin · 62 tokens

publish-branch

Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.

OutlineDriven/odin-claude-plugin · 60 tokens

drill

Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.

OutlineDriven/odin-claude-plugin · 67 tokens