Borrowing it
Nothing to install: this file belongs to geniro-io/geniro-claude-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/geniro-io/geniro-claude-harness/main/.claude/skills/find-threads/SKILL.mdgit clone --depth 1 https://github.com/geniro-io/geniro-claude-harnessWrote 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/geniro-io/geniro-claude-harness/find-threads)<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/find-threads"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/find-threads/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/geniro-io/geniro-claude-harness/find-threads"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/find-threads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high System Prompt Leakage · line 78 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Agent Snooping · line 249 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 | $0.00170 | $0.05277 |
| Opus 5 | $0.00085 | $0.02638 |
| Sonnet 5 | $0.00034 | $0.01055 |
| Haiku 4.5 | $0.00017 | $0.00528 |
Grade A, and why
find-threads 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 11d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/find-threads — discover work-bearing Claude threads and hand them to /analyze-thread
Contents
- Phases
- Loop invariants
- Anti-rationalization
- Definition of done
- Budgets & caps
- ACI per-phase tool surface
- Phase 1 (discover) · Searching by content
- Phase 2 (present) · Phase 3 (select & launch)
- REFERENCE
You are the orchestrator for finding past Claude Code conversation threads that did substantive agentic work and routing the ones the user picks to the existing /analyze-thread skill. The sibling scan.py enumerates every project's session logs across all config dirs, keeps threads that edited code OR ran a skill OR spawned a subagent (tagging each edited or read-only, so read-only review/debug/investigate runs are surfaced too), and — when the user passes a query — searches inside the thread bodies and ranks the matches. You present the survivors, take a free-text selection, then launch /analyze-thread on the first batch, sized to its per-run cap (its §Budgets & quality gates), and print any overflow batches as a ready-to-run queue. You only READ session logs — you never modify them, and you never edit /analyze-thread.
Input: an optional query and/or the --code-only flag in $ARGUMENTS.
- Empty → list every work-bearing thread (edited + read-only), grouped by project.
- A query (e.g.
2649,bright data,case-radar.ts,didnt post low) → keep only threads whose body, title, or project path matches, ranked best-first. See Searching by content below for what to type. --code-only→ restrict the result set to code-editing threads (the legacy behavior); combines with a query.
Output: a titled list of threads, each tagged edited or read-only, + (on the user's pick) a launched /analyze-thread <paths…> --format=jsonl directive for the first batch, plus a queue for any overflow.
Phases
- Discover — run
scan.py. It enumerates every*.jsonlsession log under each config dir'sprojects/, keeps threads that did agentic work — aneditedthread calls a code-edit tool (Edit/Write/MultiEdit/NotebookEdit); aread-onlythread spawns a subagent or invokes a Skill but never edits code — and for each survivor extracts its kind, a title, the true project label, the date, a turn count, and an oversize flag.--code-onlydrops the read-only threads. With a query it also scores each thread by content match and drops non-matches. - Present — render the survivors. No query → grouped by project, newest-first. A query → one flat list ranked best-first, each row showing its project, date, title, kind (
edited/read-only), a match indicator, and a snippet. Number every shown row. - Select & launch — take a free-text reply (
1,4,7/1-5/all), resolve it to absolute paths, echo the set for confirmation, then launch/analyze-threadon the first batch, sized to its per-run cap (its §Budgets & quality gates), and print any overflow as a runnable queue.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 251 lines · 170 tokens per session scan A 32d730126972
find-threads is a skill published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed today), licensed Apache-2.0. It adds 170 tokens to every session and 5,277 once invoked, about $0.0009 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.