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/baizhiyuan/finding-unknowns-skillWrote 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/commands/baizhiyuan/finding-unknowns-skill/cartographer)<a href="https://agentmods.dev/commands/baizhiyuan/finding-unknowns-skill/cartographer"><img src="https://agentmods.dev/badge/commands/baizhiyuan/finding-unknowns-skill/cartographer/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/commands/baizhiyuan/finding-unknowns-skill/cartographer"><img src="https://agentmods.dev/badge/commands/baizhiyuan/finding-unknowns-skill/cartographer.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 | $0.00025 | $0.00334 |
| Opus 5 | $0.00013 | $0.00167 |
| Sonnet 5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
cartographer 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 9d 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
cartographer
Direct entry into Cartographer mode, skipping lightweight-lane routing.
Dispatch
- Read the full skill instructions from
skills/finding-unknowns/SKILL.mdin this plugin (or~/.claude/skills/finding-unknowns/SKILL.mdfor manual installs). - Jump to Phase C: Cartographer mode and follow it exactly — resolve and announce the
clarity threshold (first line), run the Round 0 topology gate, seed the ledger (C0),
run the score-gated clearing loop (C1) with the standard round-report template
(four-quadrant score table every round), enforce the dual coverage+ambiguity gate (C2),
and end at the approval-gated execution bridge (Phase E). Delegate ledger bookkeeping
and quadrant scoring to the
ledger-keeperagent when installed. - Depth flags map to threshold presets:
--quick0.35 ·--standard0.25 (default) ·--deep0.15. A flag overrides any settings value; announce the source accordingly. - Treat the user's remaining arguments as the task under investigation:
$ARGUMENTS
If no arguments were given, ask for the task first; do not seed a ledger for an unstated goal.
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.
- 9d ago First seen · 30 lines · 25 tokens per session scan A 556de52c0031
cartographer is a command published in the GitHub repository baizhiyuan/finding-unknowns-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 334 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 commands, from other repositories
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
triage
Interactive triage. Mark each finding TP / FP / wontfix. Feeds the active-learning loop for next scan.
labs
Experimental + AI-driven. Self-audit, model rescan, rule synth, cross-repo, risk/time quantification.