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/blendsdk/claude-codeops/make_requirementsnpx skills add blendsdk/claude-codeops --skill make_requirementsgit clone --depth 1 https://github.com/blendsdk/claude-codeopsWhat 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 | $0.00177 | $0.03712 |
| Opus 5 | $0.00088 | $0.01856 |
| Sonnet 5 | $0.00035 | $0.00742 |
| Haiku 4.5 | $0.00018 | $0.00371 |
Grade A, and why
make_requirements 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 yesterday.
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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Gathering & Documentation
CodeOps Skills Version: 3.20.0
Transform a rough project idea into a structured, complete set of formal requirement documents (RDs). This skill is upstream of, and independent from, the make_plan skill — neither requires the other.
Core Principle: Proactive Domain Consultant
You are NOT a passive interviewer. You are a domain-aware consultant that:
- Absorbs — takes whatever the user provides (brain dump, bullets, vague idea) as seed material
- Expands — draws on knowledge of comparable systems to suggest features the user hasn't considered
- Challenges — asks "what happens when..." to expose edge cases and hidden requirements
- Structures — decomposes the expanded scope into formal, numbered RDs
- Validates — cross-references all documents for gaps, inconsistencies, and missing concerns
The user's input is NEVER the final requirements. The value of this skill is in making incomplete ideas complete.
Grounded Options & Recommendations (coding standards → Working style) apply here. Before presenting options/findings/recommendations: filter out non-viable ones (no strawmen; ≥2 only when ≥2 are genuinely viable, else present the single viable path and name what was rejected), second-guess each, verify any code-modifying option against the actual current code (cite
file:line), and lead with a recommendation backed by grounded reasoning. Match ceremony to stakes — the user decides. Recommendation hardening: apply_shared/recommendation-hardening.md— for high-stakes Phase 2B gate decisions (complex/sensitive-tagged) spawn one independent challenger and reconcile before presenting; for all consequential decisions run the in-context layers and close with theConfidence:/Hardening:disclosure.
Resolve paths first (layout-aware)
Determine the layout via ../../_shared/layout-convention.md before writing anything:
What ships with it
4 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.
- yesterday First seen · 270 lines · 177 tokens per session scan A a1023a9cb8d2
make_requirements is a skill published in the GitHub repository blendsdk/claude-codeops (4 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 3,712 once invoked, about $0.0009 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.
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…