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.
git clone --depth 1 https://github.com/desplega-ai/agent-swarmWrote 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/desplega-ai/agent-swarm/implement-issue)<a href="https://agentmods.dev/commands/desplega-ai/agent-swarm/implement-issue"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/implement-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/desplega-ai/agent-swarm/implement-issue"><img src="https://agentmods.dev/badge/commands/desplega-ai/agent-swarm/implement-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 | $0.00015 | $0.00665 |
| Opus 5.5 | $0.00006 | $0.00266 |
| Sonnet 5.5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
implement-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 26d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Issue
Read a GitHub or GitLab issue, implement the requested changes, and create a PR/MR.
Provider detection: Check the URL or remote:
- If GitHub → use
gh issue view/gh pr create - If GitLab → use
glab issue view/glab mr create
Arguments
issue-number-or-url: Either an issue number (e.g.,123) or a full URL
Workflow
1. Parse and Fetch
If given a URL, extract owner, repo, and issue number. Fetch issue details (title, body, labels, comments). Understand what's being requested, acceptance criteria, and any technical constraints.
2. Setup
- Ensure repo is cloned to
/workspace/personal/<repo-name>(clone withgh repo cloneif needed) - Fetch origin, checkout main, pull latest
- Create a feature branch:
fix/issue-<number>-<short-description>
3. Implement
- Understand the codebase — explore relevant files and existing patterns
- Plan your approach — consider using
/planningfor complex changes - Write the code — implement the requested functionality
- Test your changes — run existing tests, add new tests if appropriate
- Verify it works — manual verification where possible
Keep changes focused on what the issue requests. Avoid scope creep.
4. Quality Checks, Commit, and Push
- Run PR checks (MANDATORY) — Run ALL checks from the "PR Checks" section of your Repository Guidelines. Fix any failures before proceeding. If no guidelines are defined, check the project's CLAUDE.md for a pre-PR checklist.
- Commit with a message referencing the issue (e.g.,
Fix #123: <description>). Use conventional commit style if the repo uses it. - Push with
git push -u origin HEAD.
5. Create the PR
Create the PR with a descriptive title and a body that follows the repository's PR template and conventions (see /create-pr, steps 5 and 6). If the repo defines none, include: summary of changes, key changes list, and testing done. Always include Fixes #<issue-number> to auto-close the issue on merge.
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.
- 26d ago Changed 61ccea5cd46b
- 1mo ago First seen · 63 lines · 15 tokens per session scan A a12d96338dcf
implement-issue is a command published in the GitHub repository desplega-ai/agent-swarm (910 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 665 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 commands, from other repositories
tokenless-stats
Show Tokenless compression statistics.
rollback
An interactive Git command for moving a branch back to an earlier commit, tag, or saved reference. It supports reset, which changes branch history, and revert, which adds new commits that undo earlier ones.
clean-branches
A Git command for finding and safely removing local or remote branches that are already merged or have not been updated for a chosen number of days. Git branches are separate lines of code history used for features, fixes, or experiments.
merge
Consolidate feature branch changes and create final PR to main. This completes the v5.0 feature branch workflow after all task PRs have been merged.
update
Check for and apply KARIMO updates from GitHub releases.
cct-sop-alert
A command that runs a marketing-scoring notification workflow for testing DingTalk alerts. DingTalk is a team-messaging service used for notifications.