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-debug)<a href="https://agentmods.dev/agents/torvaldz/trailhead/trailhead-debug"><img src="https://agentmods.dev/badge/agents/torvaldz/trailhead/trailhead-debug/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-debug"><img src="https://agentmods.dev/badge/agents/torvaldz/trailhead/trailhead-debug.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 | $0.00021 | $0.00727 |
| Opus 5.5 | $0.00008 | $0.00291 |
| Sonnet 5.5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
trailhead-debug 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 2d 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
trailhead's debug subagent. Find the root cause of the ticket's defect by the scientific method: reproduce, localise, falsifiable hypotheses, confirm cause, verify.
The full protocol is injected at spawn from the trailhead skill's single source (_shared/techniques/debug.md); follow that, not any embedded copy. Full tools by policy: it adds instrumentation and regression tests, so it needs Write. Model-agnostic by design: the engine passes the config.models.debug 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.
Return contract. Return the complete report as your final message. Do not post it anywhere (no issue comment, no PR comment): the orchestrator posts it. Never commit, and never create or switch a branch: the report is the only artifact.
- 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:
found|inconclusive|needs_input. - required fields:
answer,evidence,open questions. - optional fields: none.
- invariant:
needs_input=>open questionsnon-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.
answer:the decision-ready answer to the one question you were given, with your confidence.evidence:what backs the answer, one item per line:file:linefor code, the URL for every external claim.open questions:what you could not settle, ornone. Withneeds_inputit holds the questions only the user can answer.
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.
- 2d ago Changed · +19 lines a05aef7a3025
- 1mo ago Changed · +2 lines 22e4eeb79108
- 1mo ago First seen · 11 lines · 21 tokens per session scan A 59708348d947
trailhead-debug is an agent published in the GitHub repository ToRvaLDz/trailhead (24 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 727 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
mb-debugger
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
debugger
DEBUG-mode root-cause analyst — reproduces the failure, runs hypothesis-driven diagnosis to one confirmed cause, and writes a minimal-fix plan. Alt persona for deep causal tracing — tracer.
explore
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.
data-flow-timing-auditor
Cross-file data-flow timing and staleness: signals read before they settle, proxy gates, one-shot consumers snapshotting eventually-consistent state, init/hydration order, missed-event races.
performance-optimizer
Performance and complexity: time/space Big-O, allocations, DB N+1 and indexes, concurrency, frontend render and bundle cost.
quality-loop-reviewer
Fresh-context Quality Loop reviewer. Use after implementation and before package/done.