Borrowing it
Nothing to install: this file belongs to nick-pape/grackle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nick-pape/grackle/main/.claude/skills/write-spec/SKILL.mdgit clone --depth 1 https://github.com/nick-pape/grackleWrote 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/nick-pape/grackle/write-spec)<a href="https://agentmods.dev/skills/nick-pape/grackle/write-spec"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/write-spec/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/nick-pape/grackle/write-spec"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/write-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.01528 |
| Opus 5.5 | $0.00012 | $0.00611 |
| Sonnet 5.5 | $0.00006 | $0.00306 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
write-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 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Spec — Requirements Specification Writer
This skill researches a GitHub issue in depth and writes a detailed requirements specification directly into the issue body.
Step 0: Parse Arguments
The issue number must be provided as an argument. If not provided, ask the user for the issue number and stop.
ISSUE_NUMBER=<provided argument>
REPO="nick-pape/grackle"
Step 1: Read the Issue
gh issue view $ISSUE_NUMBER -R $REPO
Capture the title, body, labels, and any referenced issues (parent epics, related issues, sibling tickets).
Step 2: Read Related Issues
For every issue referenced in the body (parent epics, sibling sub-tasks, related features), read them:
gh issue view <RELATED_NUMBER> -R $REPO
This provides context on how this issue fits into the larger feature.
Step 3: Read Relevant Specs and RFCs
Check these spec files in the repo for relevant sections:
specs/2026-03-18-agent-kernel.md— Agent Kernel Architecture RFC (task lifecycle, process model, scheduling, IPC, signals)specs/2026-03-11-grackle-deep-dive.md— Full architecture deep dive (all subsystems)specs/2026-02-20-v0.md— Original design spec (UI mockups, interaction patterns)specs/2026-03-13-default-personas.md— Persona roster definitionsspecs/2026-03-12-ux-audit.md— UX audit findings and recommendations
Read the files that are relevant based on the issue's domain (server, web, CLI, powerline, etc.). Use the issue labels to guide which specs to prioritize.
Step 4: Read Relevant Source Code
Based on the issue's domain, explore the codebase to understand the current state:
- Server issues:
packages/server/src/— stores, gRPC service, event processor, adapters - Web/UX issues:
packages/web/src/— components, hooks, routing, existing UI patterns - CLI issues:
packages/cli/src/— commands, formatters - PowerLine issues:
packages/powerline/src/— MCP tools, runtimes, adapters - Proto issues:
packages/common/src/proto/— existing messages, RPCs, enums - Common/types:
packages/common/src/types.ts— shared type definitions
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 · 141 lines · 29 tokens per session scan A 7f69293cfa95
write-spec is a skill published in the GitHub repository nick-pape/grackle (22 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,528 once invoked, about $0.0001 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
kanban-tasks
A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.
configure-coddy
Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands for config.yaml and commits only after the user confirms saving; MCP servers are entries of the mcp.json files. Load…
crossreview
Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review (uncommitted work, a branch, a commit range, files, a plan or a document) out to several console code agents (Claude…
rpa-init
Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository. The agent studies code, reads documentation and test code, sets up the dev environment as the project expects, runs tests, and writes a short project report. No extra user brief is required.
rpa-gen-rules
Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.
rpa-feat
Run when the user invokes /rpa-feat together with a clear feature description (for example issue text). BDD workflow: plan, failing tests, implementation, green tests, full suite, docs and examples, linter at the end. Will not work correctly without the user supplying what to build.