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 agentmods add commands/desplega-ai/agent-swarm/respond-githubgit clone --depth 1 https://github.com/desplega-ai/agent-swarmWhat 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 | $0.00014 | $0.00366 |
| Opus 5 | $0.00007 | $0.00183 |
| Sonnet 5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
respond-github 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.
What it actually says
Respond to VCS Issue/PR/MR
Post a response to a GitHub issue/PR or GitLab issue/MR.
Provider detection: Check the URL or remote:
- If GitHub → use
gh issue comment/gh pr comment - If GitLab → use
glab issue note/glab mr note
Arguments
issue-or-pr-number-or-url: Either a number (e.g.,123) or a full URL
Workflow
- Parse the input — if given a URL, extract owner, repo, type (issue/PR), and number. If just a number, determine type from current repo context.
- Ensure repo is cloned to
/workspace/personal/<repo-name>(clone withgh repo cloneif needed). - Get full context — read the original description and all comments in the thread.
- Understand what's being asked — if this is from
@agent-swarm, focus on what was asked in that mention. - Formulate and post your response using
gh issue comment/gh pr comment(orglabequivalents).
Decision Framework
- What specific question or request needs addressing?
- Do you need to provide code examples?
- Should you ask clarifying questions?
- Is this something you can resolve, or do you need human input?
Tips
- Check if there's already a PR addressing an issue before responding
- For complex requests, acknowledge receipt and outline your plan
- If you've completed work, link to the relevant PR or commit
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 First seen · 38 lines · 14 tokens per session scan A 4d314981fdda
respond-github is a command published in the GitHub repository desplega-ai/agent-swarm (729 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 366 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
update-plan
Update project plan from repo state and conversation.
distill
Distill repository files into the RLM Summary Ledger using agentic intelligence (fast) or Swarm Workers (offline batch).
distill-agent
High-speed RLM distillation of project documentation using agentic intelligence.
os-loop
Run a full OS improvement cycle — execute, eval, emit friction events, close with post-run metrics, and trigger a Triple-Loop Retrospective if the friction threshold is crossed.
os-architect
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.
os-init
Bootstrap the project by triggering the agentic-os-setup conversational architect.