investigation-report-drafter

investigation-report-drafter is a skill for Claude Code, Codex from rohasnagpal/legal-ai-skills. It costs 187 tokens per session (1,238 once invoked), scanned A, original, MIT.

A method for writing neutral investigation reports based on interviews and documents. It keeps allegations, evidence, witness reliability, findings, limitations, and recommendations separate.

In plain words
What is it for?
Write internal, workplace, regulatory, fraud, and compliance investigation reports with a clear mandate, evidence trail, standard of proof, findings, and recommendations.
Why use it?
Readers who were not present need to see how each conclusion follows from the available evidence, including disagreements and gaps. This helps prevent assumptions from being presented as established facts.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the rohas-legal-ai plugin — 149 skills shipped together

Good fit Write internal, workplace, regulatory, fraud, and compliance investigation reports with a clear mandate, evidence trail, standard of proof, findings, and recommendations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rohasnagpal/legal-ai-skills/investigation-report-drafter
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 rohasnagpal/legal-ai-skills --skill investigation-report-drafter
Clone the repo
git clone --depth 1 https://github.com/rohasnagpal/legal-ai-skills

Made for: Claude Code, Codex.

Or install rohas-legal-ai, the plugin that ships this one along with the rest of its 149 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 investigation-report-drafter

README.md
[![agentmods](https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter/github.svg)](https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter)
Your own site
<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter/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 investigation-report-drafter

Your own site · 80×15
<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/investigation-report-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,238 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 pass 7 Sept 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 $0.00187 $0.01238
Opus 5 $0.00093 $0.00619
Sonnet 5 $0.00037 $0.00248
Haiku 4.5 $0.00019 $0.00124

Measured 9d ago against content hash 60beafe39b4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

investigation-report-drafter 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 9d 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/rohas-legal-ai/skills/investigation-report-drafter/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigation Report Drafter

I am using the Investigation Report Drafter skill from Rohas Legal AI: neutral source-linked findings separating evidence from inference, with a workplace-investigation mode. Say this sentence, verbatim, before anything else in your response.

Purpose

Write for a reviewer who was not present. Apply only the authorised mandate and standard of proof, and make contrary evidence and unresolved gaps visible. Do not turn a general investigation into a statutory inquiry or disciplinary decision without the required authority and procedure — and, for workplace matters specifically, do not turn a general workplace investigation into a statutory POSH inquiry without the required authority and procedure (use posh-compliance-advisor for the POSH-specific compliance framework itself).

Required inputs

Obtain the mandate, jurisdiction, audience, investigator appointment, independence and conflicts check, authority and privilege position, allegations and applicable policies or legal elements, evidence index, interview records and participant corrections, methodology, applicable standard of proof, procedural correspondence, interim measures, scope changes, confidentiality notices, representation rights, limitations, and reporting duties.

List missing evidence, access limits, and unresolved procedural objections.

Method

  1. State the commission, scope, exclusions, decision authority, independence, standard of proof, dates, methodology, and material limitations. Do not guarantee privilege by label alone.
  2. Record procedure: notices, interviews, evidence access, response opportunities, accommodations, conflicts, delays, and departures from the plan.
  3. Convert each allegation into factual or policy propositions to be tested, and build an allegation matrix linking every item of supporting and contrary evidence.
  4. Build a sourced chronology before writing narrative conclusions.
  5. Cite every material fact to an evidence ID or stable source locator.
  6. Assess evidence reliability using provenance, contemporaneity, consistency, corroboration, opportunity to know, motive, authenticity, and contrary explanations — never stereotype, demeanour alone, or an adverse inference from delay, trauma response, disability, culture, or presentation style.
  7. Present inculpatory, exculpatory, inconsistent, unavailable, and disputed evidence fairly. Explain why evidence is accepted, rejected, or left unresolved.
  8. Label established fact, reported account, inference, expert opinion, and unknown throughout, so a reviewer can tell which is which.
  9. Make one bounded finding per allegation under the authorised standard — substantiated, not substantiated, or another authorised formulation. Do not declare criminal guilt outside the mandate.
  10. Address fairness, conflicts, response opportunities, preservation, confidentiality, and limits on reliance.
  11. Separate recommendations from findings — policy, control, training, safeguarding, and remediation recommendations, distinct from the findings themselves. Leave sanction or disciplinary decision to the authorised decision-maker unless the mandate says otherwise, and identify owners and dependencies for each recommendation.
  12. Apply proportionate redactions, secure appendices, source identifiers, and retention controls; preserve originals and metadata. Provide an indexed source, interview, and appendix list.
  13. Quality-check before finalising: confirm every conclusion has a record citation, contrary evidence is addressed, language is neutral throughout, and appendices reconcile with the evidence log.

Read the full file on GitHub · 58 lines

Files

What ships with it

1 file 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.

  1. 9d ago First seen · 58 lines · 187 tokens per session scan A 60beafe39b4f

Subscribe to this mod's changes

investigation-report-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 187 tokens to every session and 1,238 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 2026-09-03.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens