investigue

investigue is a skill for Claude Code from naiersaidane/claude-mastery. It costs 128 tokens per session (626 once invoked), scanned A, original, MIT.

A structured bug-investigation process that first locates and reproduces the problem, then ranks three possible root causes and gathers targeted logs before making a minimal fix.

In plain words
What is it for?
Use it when software crashes or behaves differently from what you expect, provided you can describe both the observed and expected behavior.
Why use it?
It prevents jumping to an untested solution and separates the visible symptom from the underlying cause. Each phase pauses for your validation before continuing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-mastery plugin — 8 skills shipped together

Good fit Use it when software crashes or behaves differently from what you expect, provided you can describe both the observed and expected behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/naiersaidane/claude-mastery/investigue
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 naiersaidane/claude-mastery --skill investigue
Clone the repo
git clone --depth 1 https://github.com/naiersaidane/claude-mastery

Made for: Claude Code.

Or install claude-mastery, the plugin that ships this one along with the rest of its 8 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 investigue

README.md
[![agentmods](https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/investigue/github.svg)](https://agentmods.dev/skills/naiersaidane/claude-mastery/investigue)
Your own site
<a href="https://agentmods.dev/skills/naiersaidane/claude-mastery/investigue"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/investigue/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 investigue

Your own site · 80×15
<a href="https://agentmods.dev/skills/naiersaidane/claude-mastery/investigue"><img src="https://agentmods.dev/badge/skills/naiersaidane/claude-mastery/investigue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 626 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
  • Socket pass 15 Jun 2026
  • Snyk pass 15 Jun 2026
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 $0.00128 $0.00626
Opus 5 $0.00064 $0.00313
Sonnet 5 $0.00026 $0.00125
Haiku 4.5 $0.00013 $0.00063

Measured 12d ago against content hash 31b4be68913c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

investigue 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 12d 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.

skills/investigue/SKILL.md · 29 lines

What it actually says

Avant de commencer, vérifie que tu disposes de deux éléments :

  • Le symptôme : ce qui se passe concrètement (message d'erreur, comportement observé, valeur retournée…)
  • Le comportement attendu : ce qui devrait se passer à la place

Si l'un ou l'autre manque, demande-le explicitement avant d'aller plus loin.


Avant tout fix, déroule ces 4 phases dans l'ordre. Arrête-toi à la fin de chacune et attends ma validation.

PHASE 1 : Localiser et reproduire.

À partir du symptôme, explore le code (utilise le sous-agent Explore si nécessaire) pour identifier les 2-3 zones les plus susceptibles d'héberger la cause. Liste-les avec une phrase de justification chacune. Puis décris en 3 lignes le scénario minimal qui rejoue ce bug à coup sûr. Si tu ne peux pas le reproduire de manière fiable, dis-le et propose un plan pour y arriver.

PHASE 2 : 3 hypothèses classées sur la cause racine.

Propose 3 hypothèses sur la cause racine (pas le symptôme), classées de la plus probable à la moins probable. Pour chacune : hypothèse en 1 phrase, puis prédiction falsifiable — « si cette hypothèse est vraie, on observerait <observation précise> ; si on observe l'inverse, on l'élimine ».

PHASE 3 : Tester l'hypothèse #1.

Ajoute des logs ciblés pour vérifier l'hypothèse #1. Préfixe chaque log par le tag [DEBUG-a4f2] (4 caractères au hasard) pour suppression en bulk plus tard. Ne propose pas de fix à cette phase. Dis-moi ce que je dois observer pour confirmer ou infirmer.

Règle des 3 strikes : si les 3 hypothèses sont fausses, STOP. Ce n'est plus un bug de code, c'est une question d'architecture. On change d'angle.

PHASE 4 : Fix minimal.

Une fois l'hypothèse confirmée, propose les modifications les plus courtes qui traitent la cause racine. Pas d'optimisation collatérale, pas de refactor opportuniste. Rédige le message de commit en expliquant la cause racine, pas le symptôme.

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. 12d ago First seen · 29 lines · 128 tokens per session scan A 31b4be68913c

Subscribe to this mod's changes

investigue is a skill published in the GitHub repository naiersaidane/claude-mastery (51 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 626 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

spark-engineer

Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…

Jeffallan/claude-skills · 75 tokens

debugging-wizard

Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting…

Jeffallan/claude-skills · 70 tokens

Reverse Engineering & Binary Analysis

Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.

Masriyan/Claude-Code-CyberSecurity-Skill · 26 tokens

perf-profiler

A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.

laolaoshiren/claude-code-skills-zh · 78 tokens

log-analyzer

A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.

laolaoshiren/claude-code-skills-zh · 24 tokens

lcx-report-bug

Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.

code-yeongyu/oh-my-openagent · 85 tokens