blind-rediscovery

blind-rediscovery is a skill for Claude Code from mtarcure/claude-vibe-squad. It costs 67 tokens per session (1,553 once invoked), scanned A, original, MIT.

An operational checklist and helper for exploring several targets without revealing earlier findings to each exploration. It separates voice-readable dossiers from private comparisons.

In plain words
What is it for?
It is for coordinating blind, multi-target research and organizing the resulting dossiers.
Why use it?
It reduces the risk that previous results bias a fresh investigation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the chrono-vault plugin — 3 skills shipped together

Good fit It is for coordinating blind, multi-target research and organizing the resulting dossiers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mtarcure/claude-vibe-squad/blind-rediscovery
Install

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.

Any agent
npx skills add mtarcure/claude-vibe-squad --skill blind-rediscovery
Clone the repo
git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad

Made for: Claude Code.

Or install chrono-vault, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for blind-rediscovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/blind-rediscovery/github.svg)](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/blind-rediscovery)
Your own site
<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.

agentmods 80×15 button for blind-rediscovery

Your own site · 80×15
<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>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash c0703f9986c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

plugins/chrono-vault/skills/blind-rediscovery/SKILL.md · 113 lines

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

Read the full file on GitHub · 113 lines

Changes

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.

  1. 7d ago First seen · 113 lines · 67 tokens per session scan A c0703f9986c9

Subscribe to this mod's changes

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.