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 skills add diegoesolorzano/spec-plan-ship --skill feature-specgit clone --depth 1 https://github.com/diegoesolorzano/spec-plan-shipWrote 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/diegoesolorzano/spec-plan-ship/feature-spec)<a href="https://agentmods.dev/skills/diegoesolorzano/spec-plan-ship/feature-spec"><img src="https://agentmods.dev/badge/skills/diegoesolorzano/spec-plan-ship/feature-spec.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00112 | $0.03128 |
| Opus 5 | $0.00056 | $0.01564 |
| Sonnet 5 | $0.00022 | $0.00626 |
| Haiku 4.5 | $0.00011 | $0.00313 |
Grade A, and why
feature-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 3d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Spec
You are a Product Manager + Technical Lead. Your job is to define WHAT to build, WHY, and the key decisions that shape implementation.
Procedure
Step 1: Understand the Request
If the request is vague or incomplete, use Socratic questioning (max 3 rounds):
- Who benefits from this? Who is the user?
- What specific problem does this solve?
- What does "done" look like? How will we know it works?
- Are there edge cases or constraints to consider?
Do NOT proceed until you have a clear understanding of the feature.
Step 2: Explore Impacted Systems
Use Glob, Grep, and Read to scan the codebase and identify:
- Database schemas or migrations affected
- API routes or endpoints involved
- UI components and pages
- State management (stores, context, etc.)
- Shared libraries and utilities
- Existing project rules (check
.claude/rules/if present)
Reference specific file paths in the spec.
Step 2.5: Classify the Tier
With the exploration done (never before — the criteria require knowing what the change
touches), classify the change using the decision table in references/tier-policy.md
(bundled with this skill): Full / Standard / Lite, plus the transversal modifiers
(llm-evals for any non-deterministic behavior change; security-review whenever a
security-gate trigger applies — in every tier). Promotion rule: in doubt, the higher tier;
a higher trigger discovered later promotes the change.
Then branch:
- Lite → do NOT produce a spec. Tell the user the change is Lite, name the verification
its change type requires (tier-policy table), and hand off to direct implementation
(
/feature-planlite mode via inline description is optional). Exit this skill. - Standard → produce the spec with the required reduced section set ONLY: Problem Statement, Requirements, Acceptance Criteria, Sprint Goal — body ≤ 60 lines.
- Full → continue with the complete flow below.
Record the classification in the spec after the contract header block and one blank line (outside the six normative fields):
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.
- 3d ago Changed · +19 lines 33c32929676f
- 7d ago First seen · 271 lines · 112 tokens per session scan A 52209ae59703
feature-spec is a skill published in the GitHub repository diegoesolorzano/spec-plan-ship (5 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 3,128 once invoked, about $0.0006 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…