Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PaulDuvall/ai-development-patternsnpx agentmods add skills/paulduvall/ai-development-patterns/evaluate-pattern-adoptionWrote 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/paulduvall/ai-development-patterns/evaluate-pattern-adoption)<a href="https://agentmods.dev/skills/paulduvall/ai-development-patterns/evaluate-pattern-adoption"><img src="https://agentmods.dev/badge/skills/paulduvall/ai-development-patterns/evaluate-pattern-adoption/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/paulduvall/ai-development-patterns/evaluate-pattern-adoption"><img src="https://agentmods.dev/badge/skills/paulduvall/ai-development-patterns/evaluate-pattern-adoption.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02288 |
| Opus 5.5 | $0.00027 | $0.00915 |
| Sonnet 5.5 | $0.00014 | $0.00458 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade A, and why
evaluate-pattern-adoption 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Pattern Adoption
Run model-backed research only in the user's interactive local Codex client. Keep GitHub Actions deterministic and credentialless for this capability.
Establish the execution boundary
- Work from the repository root in a local Codex app, CLI, or IDE session signed in with the user's ChatGPT account. Prefer the Codex app.
- Confirm that evaluation will use the active Codex authentication. Local execution alone does not determine billing: a signed-in ChatGPT-plan client uses that plan's Codex allowance or credits, while API-key authentication is billed as OpenAI Platform API usage.
- Do not continue when
GITHUB_ACTIONS=true, when an evaluator API-key environment variable is present, or when the active client is authenticated with an API key. Never request, read, copy, print, or store a provider key. - Do not treat the user's initial request as approval to spend agent credits or publish results. Both gates below occur after the relevant plan or diff exists.
- Fetch
origin, then start from a dedicated branch or worktree whoseHEADis the currentorigin/main. Requiregit status --shortto be empty before planning. Do not stash, discard, absorb, or work around unrelated changes; stop and move to a clean worktree instead. - Confirm there are no unrelated tracked or untracked changes under
verification/or inexperiments/NOTES.md. The final scope validator intentionally examines the whole worktree and fails on every changed path outside the approved run.
Read references/evidence-methodology.md completely before starting research.
Build the deterministic plan
Choose one explicit scope:
stale— up to 10 missing, legacy, or stale patterns by default;stable— every stable pattern inpatterns.yaml;exploratory— every pattern inexperiments/README.md;all— stable plus exploratory patterns and one discovery unit;single— one exact catalog name; ordiscovery— discovery only, with no evidence pattern.
What ships with it
2 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.
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.
- 1mo ago First seen · 135 lines · 68 tokens per session scan A edc0c656a5e4
evaluate-pattern-adoption is a skill published in the GitHub repository PaulDuvall/ai-development-patterns (666 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 2,288 once invoked, about $0.0003 per session on Opus 5.5. 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
session-retrospective
Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…
ralph
Launcher for the Ralph-style queue drain script — emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one claude -p --worktree per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph…
adopt-project-scope
Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
quick-start
Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me…
review-proposals
Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…