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/analyze-thread/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/analyze-thread)<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/analyze-thread"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/analyze-thread/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/analyze-thread"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/analyze-thread.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 216 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 | $0.00212 | $0.05785 |
| Opus 5 | $0.00106 | $0.02892 |
| Sonnet 5 | $0.00042 | $0.01157 |
| Haiku 4.5 | $0.00021 | $0.00579 |
Grade A, and why
analyze-thread 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 4d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/analyze-thread — post-hoc Claude thread failure analyzer
Contents
- Phases
- Subagent model tiering
- State persistence
- Loop invariants
- Anti-rationalization
- Budgets & quality gates
- ACI per-phase tool surface
- Definition of done
- Phase 1 (parse) · Phase 2 (detect) · Phase 3 (filter) · Phase 4 (present)
- Modifier handling
- Task execution entry / state recovery
- REFERENCE
You are the orchestrator for analyzing a saved Claude conversation thread and surfacing the errors Claude made while running a multi-phase pipeline. You parse the thread, run mechanical and judged checks against the canonical taxonomy, filter for relevance, then present findings with per-item user gates. You never mutate the analyzed source files (this skill is read-only on the project under analysis); approved fixes are emitted as a handoff for /improve-template to apply.
Input: one or more thread file paths, a thread count, or nothing — an empty argument analyzes the last 3 work-bearing threads across every project (§Phase 1 Step 1).
Output: a findings report printed to chat + (on user approval) a handoff at .geniro/state/handoff/from-analyze-thread-<branch>.md that /improve-template consumes.
Phase bodies. This file is the spine — role, invariants, gates, phase map. Read the phase's Steps on entry to that phase, from .claude/skills/analyze-thread/: phase-1-2-parse-detect.md (Phases 1-2) · phase-3-4-filter-present.md (Phases 3-4). That Read is the phase's physically-first action and carries a one-line echo, per skills/_shared/phase-entry-read.md — the phase files hold this skill's gates (including the Phase 4 user gates and the handoff emit) and their helper call sites, so work started before the Read runs outside them.
After a compaction: re-Read the phase file for whatever phase is running before continuing it — only the front-loaded prefix re-attaches, so a mid-phase summary can drop the Steps while leaving this spine intact. If which phase was running is also gone, re-invoke /analyze-thread with the same argument — the §State persistence checkpoint makes that a resume, not a re-run.
What ships with it
4 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.
- 4d ago Changed fa4def665bc6
- 9d ago First seen · 217 lines · 212 tokens per session scan A ad79087a1fdb
analyze-thread is a skill published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 212 tokens to every session and 5,785 once invoked, about $0.0011 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.