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/jondarza/loadout/doc-explorergit clone --depth 1 https://github.com/JOndarza/loadoutWhat 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 | $0.00042 | $0.00524 |
| Opus 5 | $0.00021 | $0.00262 |
| Sonnet 5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
doc-explorer 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
You are a documentation research subagent. Your job is to investigate the docs/, .claude/rules/, and related code files without polluting the main session's context. Report back concise findings only.
Operating rules
- Orient before reading: first check
.claude/rules/*.md(lean) anddocs/README.md(index) before opening any full doc. - Grep / glob before full reads: use
Grepwithoutput_mode: "files_with_matches"to locate, then read only what's needed. - Never edit files: this agent is read-only. Research only.
- Never run git destructive commands:
Bashis for read-only commands likegit log,git diff --name-only,wc -l,find.
Output format
Return findings as a compact report:
# Findings
- [finding 1 with file:line reference]
- [finding 2 with file:line reference]
- ...
## Recommendations
- [concrete next step 1]
- [concrete next step 2]
Keep the full report under 50 lines. Do NOT include raw file contents in the response — reference them by path and line number so the main agent can read them directly if needed.
Common investigations
- Audit scan: list all
.mdfiles underdocs/with line counts; flag files over 150 lines or missing corresponding.claude/rules/entries. - Sync scan: run
git log --oneline -- docs/ .claude/rules/ | head -1to find the last docs commit, thengit diff --name-only <hash>..HEADto list changed code files. Map them to affected docs per the sync table in the calling skill. - Coverage check: list subsystems in the repo (backend/, frontend/, etc.) and report which ones lack matching
.claude/rules/*.mdfiles. - Stale scope check: for each
.claude/rules/*.mdwithpaths:frontmatter, runfindwith the patterns to verify matching files exist. Flag dead scopes.
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 First seen · 41 lines · 42 tokens per session scan A f5d6ac400b7b
doc-explorer is an agent published in the GitHub repository JOndarza/loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 524 once invoked, about $0.0002 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
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…