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/agents/task-finder/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/task-finder)<a href="https://agentmods.dev/skills/nick-pape/grackle/task-finder"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/task-finder/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/task-finder"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/task-finder.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 | $0.00031 | $0.01245 |
| Opus 5.5 | $0.00012 | $0.00498 |
| Sonnet 5.5 | $0.00006 | $0.00249 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
task-finder 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Finder — Resolve Work into (GitHub Issue + Grackle Task)
Your job is to take a piece of work — whether it's a specific issue number, a description of something to fix, or a request to pick from a backlog — and ensure it exists as both a GitHub issue and a Grackle task. You always return a resolved pair.
Repository
nick-pape/grackle
Modes
The orchestrator will invoke you in one of three modes. Determine the mode from context.
Mode A: Recommend from Backlog
Input: An epic number, label filter, or "next from backlog" instruction, plus a list of already-completed or failed tickets to skip.
- Fetch open issues via GitHub MCP matching the criteria (epic sub-issues, label filter, etc.)
- Fetch open PRs via GitHub MCP — exclude issues that already have a PR (
Closes #Nin body or issue number in branch name) - Check Grackle state — use
project_listandtask_listto find issues that already have in-progress Grackle tasks. Exclude those. - Prioritize the remaining candidates:
- Priority label:
priority:critical>priority:high> (unlabeled) >priority:low - Type:
bug>feature>refactor - Dependencies: if issue body mentions "depends on #N", it must come after #N
- Tiebreaker: lower issue number first (older)
- Priority label:
- Pick the top candidate and proceed to Resolution (below)
Mode B: Resolve a Known Issue
Input: A specific GitHub issue number (e.g., "#450").
- Verify the issue exists via GitHub MCP — fetch its title, body, labels, state
- If the issue is closed, report that and stop
- Proceed to Resolution (below)
Mode C: Create from Description
Input: A description of work that may not have a GitHub issue yet (e.g., "fix the login bug").
- Search existing issues via GitHub MCP — look for open issues with matching keywords
- If a matching issue exists, confirm it's the right one and proceed to Resolution
- If no matching issue exists, use the
/open-ticketskill to create one - Proceed to Resolution with the new issue number
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 · 108 lines · 31 tokens per session scan A a1547d1af9ea
task-finder is a skill published in the GitHub repository nick-pape/grackle (22 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,245 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.