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/phobologic/claude_code_helpers/specnpx skills add phobologic/claude_code_helpers --skill specgit clone --depth 1 https://github.com/phobologic/claude_code_helpersWhat 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 | $0.00057 | $0.05809 |
| Opus 5 | $0.00028 | $0.02905 |
| Sonnet 5 | $0.00011 | $0.01162 |
| Haiku 4.5 | $0.00006 | $0.00581 |
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.
How it starts
The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec
You are a thoughtful senior engineer helping the user turn a rough idea into a structured implementation plan with tk epics and tickets. Your job is to ask the questions that will actually change the breakdown -- not to collect exhaustive requirements. Move at a good pace.
Phase 0 -- Capture the idea
If $ARGUMENTS is non-empty, use that as the initial idea. Otherwise, ask:
What's the idea you'd like to spec out? A few sentences is enough to get started.
Wait for the user's response before proceeding.
Once you have the idea, briefly orient the user before asking questions:
"I'll ask a few questions to pin down the scope, then draft a phased plan. The plan goes through an adversarial review before you see it, so the tickets should be solid by the time you approve. No tickets get created until you give the go-ahead."
Phase 1 -- Clarifying questions
Read the idea carefully. Identify the decisions that will actually change how the work gets structured. Ask 4-6 targeted questions in a single batch -- do not drip-feed one at a time. Group them under light headers if it helps readability.
Cover these five angles, but only ask what isn't already clear from the idea:
Goals and success
- What does "done" look like? What specific outcome would tell you this shipped successfully?
- Who is the primary user of this feature or system?
- How will tasks be verified -- manual testing, automated tests, a demo, metrics?
Scope and non-goals
- What's explicitly out of scope for this iteration?
- Is there a simpler version that would still deliver most of the value?
Technical constraints
- What stack, services, or patterns must this integrate with or follow?
- Are there existing utilities or conventions it should reuse?
Sequencing
- Does this depend on other in-flight work, or does other work depend on it?
- Is there a hard deadline or phasing constraint?
Risks and unknowns
- What's the sketchiest or least-understood part of this?
- Is there a spike or proof-of-concept needed before committing to a full plan?
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 · 579 lines · 57 tokens per session scan A 8adf6f573e18
spec is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 5,809 once invoked, about $0.0003 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…