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 skills add mtarcure/claude-vibe-squad --skill blind-rediscoverygit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/skills/mtarcure/claude-vibe-squad/blind-rediscovery)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/blind-rediscovery"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/blind-rediscovery/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/skills/mtarcure/claude-vibe-squad/blind-rediscovery"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/blind-rediscovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 112 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00067 | $0.01553 |
| Opus 5 | $0.00034 | $0.00776 |
| Sonnet 5 | $0.00013 | $0.00311 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
blind-rediscovery 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 7d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blind rediscovery — operational checklist
When chrono runs blind rediscovery (e.g. "does v1.3 reproduce findings from a prior daemon run?") the validation signal IS voice independence. If a fan-out voice reads a Stage N dossier that names prior findings by ID/class, the experiment is invalid.
This skill operationalizes the _blind/ vs _curated/ split codified in CLAUDE.md "Dossier authoring convention" so the discipline becomes a checklist, not just prose.
When to use
- Running Stage 3 hypothesis exploration on a target with EXISTING saved findings
- Validating a v1.3 system pass against legacy daemon work from a predecessor project
- Any case where "did the voices arrive at this independently?" is the core question
When NOT to use
- Resuming a known finding for PoC drafting (Stage 4) — voices need the prior work
- New target with no prior chrono history — there's nothing to contaminate
- Bulk-mechanical refactor / lint pass — no judgment, no voice independence to preserve
Directory layout
For a target with the slug <target>. The casing is load-bearing: dispatch_context_builder. enforce_blind_floor() keys the dispatch-level floor on exactly this path, and the maintainer's
volume is case-insensitive, so a lowercase chrono/ here would resolve locally and fail on a
case-sensitive filesystem.
$CHRONO_VAULT_ROOT/Chrono/dossiers/<target>/
├── _blind/ # fan-out voices CAN read this
│ ├── stage-1-scope-<date>.md
│ ├── stage-2-codebase-map-<date>.md # NO prior-finding refs
│ └── ...
├── _curated/ # ONLY brain + operator read this
│ ├── prior-findings.md # F1, F2, etc — the saved work
│ ├── stage-3-synthesis-<date>.md # comparison-with-prior happens here
│ └── methodology-notes.md
├── raw-voices/ # raw fan-out outputs (also voice-readable)
└── _resume.md # session-resume index, brain-readable
What the dispatcher already guarantees
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.
- 7d ago First seen · 113 lines · 67 tokens per session scan A c0703f9986c9
blind-rediscovery is a skill published in the GitHub repository mtarcure/claude-vibe-squad (142 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,553 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
skill-installer
Install, update, trust, or inspect Codewhale skills from GitHub or local skill folders. Use when the user asks for available skills or wants a community skill installed.