A structured method for investigating questions and making evidence-based judgments. It uses techniques such as comparing explanations, checking assumptions, testing alternatives, and examining how events may affect one another.

Use it to investigate a problem, compare competing hypotheses, challenge assumptions, test possible outcomes, and produce a cited assessment.

It reduces the chance of accepting the first explanation or overlooking important evidence. It also records how the analysis supports each conclusion.

analyze — Skill by assafkip

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.

agentmods

npx agentmods add skills/assafkip/huntkit/structured-analysis

Any agent

npx skills add assafkip/huntkit --skill structured-analysis

Clone the repo

git clone --depth 1 https://github.com/assafkip/huntkit

Made for: Claude Code, Codex.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,186 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00085	$0.02186
Opus 5	$0.00043	$0.01093
Sonnet 5	$0.00017	$0.00437
Haiku 4.5	$0.00009	$0.00219

Measured 2d ago against content hash f9b716ed4647, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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 2d 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/structured-analysis/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Analysis Skill

Apply CIA/IC Structured Analytic Techniques to produce defensible, evidence-based analytical assessments. Every claim must be cited. Every judgment must trace to technique outputs.

Invocation

/analyze                          → Adaptive mode (auto-select techniques)
/analyze <technique>              → Direct mode (run one technique)
/analyze --guided                 → Guided mode (walk through all phases)
/analyze --resume <analysis-id>   → Resume or update existing analysis
/analyze --iterate <analysis-id>                → Re-run full analysis with new evidence
/analyze --iterate <analysis-id> <technique>    → Re-run specific technique(s)
/analyze --lean                   → Lean mode (abbreviated technique set)
/analyze --comprehensive          → Comprehensive mode (full rubric, adversarial + deception checks)
/analyze --no-osint               → Disable web research

Techniques: customer-checklist, issue-redefinition, restatement, brainstorm, kac, ach, inconsistencies, cross-impact, what-if, premortem, counterfactual, narratives, bowtie, opportunities, devils-advocacy, red-hat, alt-futures, deception

Flags combine: /analyze --guided --no-osint is valid.

Q Investigation System Integration

This skill is integrated into the huntkit investigation system.

Output Path Override

All analysis output goes inside the active case folder, not the project root.

When an active case exists (e.g., investigations/case-001-example/), replace every reference to analyses/{{ANALYSIS_ID}}/ with:

investigations/<active-case>/output/analyses/{{ANALYSIS_ID}}/

If no active case is identified, ask the founder which case this analysis belongs to.

Evidence Integration -- Tier 2 Local Files

When collecting Tier 2 (local file) evidence, always include the active case's collected intelligence. In addition to generic Glob discovery, explicitly search these directories:

investigations/<active-case>/investigation/targets/ -- target profiles with collection status and gaps
investigations/<active-case>/investigation/findings/ -- confirmed/assessed findings with confidence levels
investigations/<active-case>/investigation/evidence/ -- raw evidence and screenshots
investigations/<active-case>/investigation/timelines/ -- chronological event data
investigations/<active-case>/canonical/scope.md -- hypotheses and collection requirements

Read the full file on GitHub · 145 lines

Files

What ships with it

60 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.

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.

2d ago First seen · 145 lines · 85 tokens per session scan A f9b716ed4647

Subscribe to this mod's changes

analyze is a skill published in the GitHub repository assafkip/huntkit (51 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 2,186 once invoked, about $0.0004 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.

Research Testing ach agent-skills anthropic case-management claude claude-code

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens