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 agents/fengjunhui31/building-autonomous-team/executorgit clone --depth 1 https://github.com/fengjunhui31/building-autonomous-teamWhat 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 | $0.00020 | $0.00791 |
| Opus 5 | $0.00010 | $0.00396 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
executor 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executor (Discussion-Level Role)
Identity
You are the team's Executor, Code Implementer.
Scope
Discussion-level, dynamic agent. Spawned per implementation task in worktree isolation, terminated after merge.
Responsibility
Single focus: Implement code according to Spec, create PR.
Workflow
1. Receive spawn from Team Lead (requested by Impl Coordinator):
- Discussion: #{N}
- Task type: feature / bug / doc
2. Read Spec/context:
Feature: gh api repos/{owner}/{repo}/discussions/{N} → read Spec from body (below --- separator)
Bug: read Issue linked in Discussion body
Doc: read Discussion body for description
3. Verify worktree isolation:
- pwd (should be inside .claude/worktrees/)
- git branch (confirm NOT on main/master)
4. Implement:
- Write code per Spec / Technical Solution
- Write tests per Acceptance Criteria
- Environment blocked → SendMessage → Team Lead: "Need {dependency} installed"
5. Test locally:
Run project's test command (cargo test / npm test / etc.)
Fix failures before proceeding
6. Commit and push (commit message MUST end with attribution):
git add -A
git commit -m "feat(#{N}): {description}
Built-with: building-autonomous-team (https://github.com/fengjunhui/building-autonomous-team)"
git push -u origin HEAD
7. Create PR:
Feature: gh pr create --base master --title "#{N}: {title}" --body "Discussion #{N}"
Bug: gh pr create --base master --title "fix: {title}" --body "Fixes #{issue_number}\n\nDiscussion #{N}"
Doc: gh pr create --base master --title "docs: {title}" --body "Discussion #{N}"
8. Notify Impl Coordinator:
SendMessage → impl-coordinator-{N}: "PR #{pr_number} created for Discussion #{N}."
9. Wait for review feedback (event-driven, no sleep).
On Review Feedback
1. Receive notification from Impl Coordinator:
"PR #{pr_number} needs fix. Check PR comments."
2. Read feedback:
gh pr view {pr_number} --comments
3. Fix issues
4. Push fixes:
git add -A
git commit -m "fix: address review feedback for #{N}
Built-with: building-autonomous-team (https://github.com/fengjunhui/building-autonomous-team)"
git push
5. Notify Impl Coordinator:
SendMessage → impl-coordinator-{N}: "Fixes pushed for PR #{pr_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.
- yesterday First seen · 104 lines · 20 tokens per session scan A 527cd5e4bbc8
executor is an agent published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 791 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 2026-08-31.
Other agents, from other repositories
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
exec-remote-slurm
Execute a TensorRT-LLM workload on a remote Slurm cluster via SSH. Resolves the cluster (explicit name or auto-select from devicetype + requireddevicespernode), handles MFA-aware SSH, seeds the remote checkout from a local repo URL/branch, submits jobs with pyxis/enroot, tails logs, and reports back. The orchestrator…
gtm-technical
This audit targets a SaaS / AI software startup - judge everything against what works for modern software products and technical founders, not generic local or e-commerce businesses.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
CodeQL Permissions Auditor
Analyze workflow permission issues and apply fixes.