Borrowing it
Nothing to install: this file belongs to freegyes/project-ContemPlace. 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/freegyes/project-ContemPlace/main/.claude/commands/work-on-issue.mdgit clone --depth 1 https://github.com/freegyes/project-ContemPlaceWrote 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/commands/freegyes/project-contemplace/work-on-issue)<a href="https://agentmods.dev/commands/freegyes/project-contemplace/work-on-issue"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/work-on-issue/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/commands/freegyes/project-contemplace/work-on-issue"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/work-on-issue.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 | $0.00000 | $0.03889 |
| Opus 5 | $0.00000 | $0.01945 |
| Sonnet 5 | $0.00000 | $0.00778 |
| Haiku 4.5 | $0.00000 | $0.00389 |
Grade A, and why
work-on-issue 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 8d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work on issue
Execute the full planning-before-implementation workflow for a GitHub issue. The user provides an issue number or description — you handle the rest.
Arguments
$ARGUMENTS — the issue number (e.g., "#47", "47") or a short description of what to build. If a number, fetch the issue first. If a description, open a new issue.
Workflow
Phase 1: Gather context
- Fetch the issue (or create one if only a description was given). Read the full issue body. Use the GitHub MCP
get_issuetool for individual issues. - Fetch related issues referenced in the body or that share labels/topics. For bulk listing, use
gh issue list -R freegyes/project-ContemPlace --json number,title,labelsvia Bash — the GitHub MCPlist_issuestool returns enormous payloads (200K+ characters) that waste context. - Read the relevant source files — whatever the issue touches. Use the project layout in CLAUDE.md to find the right files. Read them, don't guess.
- Check memory — search MEMORY.md and topic files in the memory directory for prior context on this area.
- Check the note database — if the issue touches capture quality, linking, search, or tag behavior, use
search_notesorlist_recentvia MCP to surface real-world examples. The notes themselves are evidence of how the system behaves.
Phase 2: Hypothesis check
Before sending anything to specialist reviewers, assess whether the problem statement itself is sound. The goal is to catch a wrong frame before optimizing within it. Answer these questions and present them to the user:
- What problem does this issue solve? State it in one sentence.
- Is the problem real and current? What's the evidence — a bug, user friction, architectural smell, or an assumption? If the evidence is thin, flag it.
- Does the issue frame the solution space correctly? Or does it constrain it prematurely? (Example: issue #46 presented four options that all assumed the problem was code duplication. The actual problem was process duplication. The right answer wasn't among the four options.)
- Do the project's first principles still apply here? Check the relevant principles in
docs/philosophy.mdanddocs/decisions.md. Usually they hold — but sometimes a new problem reveals that a principle was drawn from too narrow a base. If a principle feels like it's fighting the problem rather than illuminating it, flag that tension explicitly. Don't assume first principles are sacred. - Are there better solutions if we step back from the issue's framing? Consider whether the issue is solving a symptom rather than the root cause.
- Is this the most valuable thing to work on right now? Given what else is open, does this earn its place?
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.
- 8d ago First seen · 174 lines · 0 tokens per session scan A 1591101a37df
work-on-issue is a command published in the GitHub repository freegyes/project-ContemPlace (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,889 tokens. 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 commands, from other repositories
sprint-status
A command that shows a project's current development status, including branches, unfinished work, local changes, stashed files, specification changes, and recent CI/CD results.
retro
A command that reviews a recent development sprint, a short period of planned work, using repository history and development metrics.
triage
Triage and categorize findings for the CLI todo system.
resolve_todo_parallel
Resolve all pending CLI todos using parallel processing.
ship-feature
Close out an in-progress feature — verify-done + brain ship (flip + checkpoint + brain check) + update feature MD + close run note.
template
Manage issue templates for streamlined issue creation.