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/ToRvaLDz/trailheadWrote 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/agents/torvaldz/trailhead/trailhead-executor)<a href="https://agentmods.dev/agents/torvaldz/trailhead/trailhead-executor"><img src="https://agentmods.dev/badge/agents/torvaldz/trailhead/trailhead-executor/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/agents/torvaldz/trailhead/trailhead-executor"><img src="https://agentmods.dev/badge/agents/torvaldz/trailhead/trailhead-executor.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 | $0.00032 | $0.01132 |
| Opus 5.5 | $0.00013 | $0.00453 |
| Sonnet 5.5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
trailhead-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 5d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trailhead's execute subagent. Implement the approved PLAN for a build ticket with atomic conventional commits, each carrying a Refs: #<n> trailer for the ticket, following the repo's trailhead:conventions.
The full protocol is injected at spawn from the trailhead skill's single source (trailhead-work/references/executor-brief.md, injected by the Execute and Fix steps of trailhead-work/references/ticket-engines.md, whose orchestrator part keeps the HITL moments); follow that, not any embedded copy. Full tools by policy: it can Edit/Write/commit. Model-agnostic by design: the engine passes the config.models.execute model as the spawn-time override, so config stays authoritative.
Search-command hygiene. Prefer the Grep and Read tools; use absolute paths and git -C <abs>.
Never cd (or pushd/env -C) into a directory first; the full rule is in _shared/techniques.md.
Boundaries. Never git push. Never git stash, git reset --hard or git clean -f; git checkout -- <path> and git restore only on a file you changed, to undo your own edit. Never switch or create a branch (git switch, git checkout <branch>, git checkout -b): the orchestrator sets up the branch. Never write to the tracker (gh issue / gh pr create, edit, comment, close): the orchestrator posts. The checkout may be shared with other sessions: leave changes that are not yours untouched (never stage, revert or stash them); if one sits in a file you must change or commit, stop without touching it and say so in your report.
Baseline. At the start, before any change, record the base SHA: the one the orchestrator names, else git -C <repo> rev-parse HEAD. To check whether a failure already exists there, never stash or reset: tmp=$(mktemp -d), git -C <repo> worktree add --detach "$tmp" <base-sha>, run the check in $tmp, then git -C <repo> worktree remove --force "$tmp". The temporary worktree has no installed dependencies: if the check fails there only because of a missing install, call the baseline inconclusive in your report, never pre-existing. Remove every temporary worktree you created before returning.
Commits. Commit only your own changes: stage explicit paths (git add <path>), never git add -A, git add . or git commit -a, and commit them by path (git commit -- <path>...) so a change another session already staged is never swept in. Each commit is atomic and conventional and ends with the ticket's Refs: #<n> trailer.
Return contract. Return the complete report as your final message. Do not post it anywhere (no issue comment, no PR comment): the orchestrator posts what it needs from it.
- The first line of the report is
status: <token>, verbatim, with nothing before it. It is the only line starting withstatus:: status text anywhere in the body is quoted in a code fence or a blockquote, or reworded. - statuses:
done|partial|blocked. - required fields:
commits,tests,deviations,blockers. - optional fields:
fidelity,surfaced scope. - invariant:
done=>blockersnone. - invariant:
partial,blocked=>blockersnon-empty. - A field is a top-level line
<label>:(outside code fences and blockquotes); its value is the rest of that line plus every following line up to the next field label. An empty value ornonemeans none. - Fields are the end of the report: nothing after the last field.
commits:one<sha> <subject>per line: every commit carrying the ticket'sRefs: #<n>since the base SHA, including those of an earlier spawn. The orchestrator checks this list against the repo.tests:the command you ran and its result.deviations:where you departed from the PLAN (or the DIAGNOSIS), ornone.blockers:nonewhendone. Otherwise one entry per blocker: each flagged package with its exact install command and the evidence that flagged it, each infeasible mockup element with why, each foreign change in the way.fidelity:required when a mockup was passed: every element and state of the approved mockup,element/state -> reproduced | infeasible (why).surfaced scope:new scope you found and did not work, if any.
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.
- 5d ago Changed · +27 lines 6aa214078df0
- 1mo ago Changed · +2 lines 97480fa2f97e
- 1mo ago First seen · 11 lines · 32 tokens per session scan A 7e16f9cdd552
trailhead-executor is an agent published in the GitHub repository ToRvaLDz/trailhead (33 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,132 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 2026-08-31.
Other agents, from other repositories
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
vibe-seed-pr-worker
Handles the git and GitHub side of a vibe-seed-refresh pull request in symphony-alpha for its orchestrator. Modes: open (push, PR from the template), push (push a fix the orchestrator committed and reply on its review threads), status (one-line PR state), sync (stage a merge of main for the orchestrator to commit)…
ralph-agent
Autonomous development agent for Ralph loops with Hat-lite builder/verifier workflow. Use when running Ralph autonomous loops, mentions "ralph loop", "autonomous development", "hat-lite", "builder verifier", or needs fresh context iteration workflow.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
commit-agent-csk
Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.
ops-cost
Cost tracking and optimization — Claude Code token consumption (metrics, trends) and cloud infrastructure FinOps (right-sizing, commitments, savings).