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/griffinwork40/agent-framework/specnpx skills add griffinwork40/agent-framework --skill specgit clone --depth 1 https://github.com/griffinwork40/agent-frameworkWhat 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 | $0.00041 | $0.00472 |
| Opus 5 | $0.00020 | $0.00236 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
spec 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.
This is a copy
100% identical to spec — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Triage: bugs route to /diagnose
Before speccing, detect bug-shaped inputs: crashes, error stacks, regression reports ("worked yesterday", "used to work"), platform-specific failures ("broken on X", "doesn't work when…"), or user-report framing that implies root-cause-first (not design-first). If detected, stop and redirect: "This is a debugging task, not a spec task. Route to /diagnose instead — it will isolate the root cause, then /spec can scope the fix." Do not emit a spec.
Dispatch two sub-agents in parallel. One researches the web for prior art, comparable approaches, and patterns relevant to $ARGUMENT. The other inspects the local working directory for conventions, existing artifacts, and integration points relevant to the domain. When both return, synthesize a concise spec using the domain-appropriate schema below. Present to the user for confirmation before proceeding.
Output schema by domain:
| Domain | Spec fields |
|---|---|
software |
problem, goals, non-goals, approach, key decisions, interface, file plan, test plan, open questions |
research |
problem, hypothesis, methodology, prior art positioning, expected results, publication plan, open questions |
design |
problem, user needs, constraints, solution space, prototype plan, success metrics, open questions |
business |
opportunity, risk analysis, competitive landscape, go/no-go criteria, resource plan, open questions |
| (other) | problem, goals, non-goals, approach, key decisions, deliverables, validation plan, open questions |
When domain is unspecified, infer from $ARGUMENT and the working directory. If ambiguous, use the generic (other) schema.
Epistemic confidence
Include an Epistemic confidence section at the end of every spec: summarize coverage gaps from research, flag claims that will be hard to verify, and note where human judgment will be needed.
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 · 31 lines · 41 tokens per session scan A 167e7cbb84de
spec is a skill published in the GitHub repository griffinwork40/agent-framework (23 stars, last pushed 7d ago), licensed Apache-2.0. It adds 41 tokens to every session and 472 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to spec, differing in 0 lines, and is treated as a copy.
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…