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/blindspot)<a href="https://agentmods.dev/commands/baizhiyuan/finding-unknowns-skill/blindspot"><img src="https://agentmods.dev/badge/commands/baizhiyuan/finding-unknowns-skill/blindspot.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00211 |
| Opus 5 | $0.00009 | $0.00105 |
| Sonnet 5 | $0.00004 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
blindspot 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 8d 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
blindspot
Direct entry into Technique 1 (blind-spot pass).
Dispatch
- Read
skills/finding-unknowns/SKILL.mdfrom this plugin (or~/.claude/skills/finding-unknowns/SKILL.mdfor manual installs). - Run Technique 1 — Blind-spot pass exactly as specified: establish goal and
experience level, explore the territory before asking anything, and report in the five
standard sections (Landmines, Hidden context, What good looks like, Questions you
should be asking, Rewritten request). Delegate to the
blindspot-scoutagent when a real codebase or domain sweep is involved. - Treat the user's arguments as the goal/area to probe:
$ARGUMENTS
Discovery ends at understanding — never continue into implementation from this command.
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.
- 8d ago First seen · 25 lines · 18 tokens per session scan A d9c0ba87d158
blindspot is a command published in the GitHub repository baizhiyuan/finding-unknowns-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 211 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
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.
elite-review
Run an elite, high-scrutiny Claude review against the current git workspace.