agentmods.dev

report-writer

report-writer is an agent for Claude Code from Liberty91LTD/cti-skills. It costs 33 tokens per session (648 once invoked), scanned A, original, MIT.

An intelligence-report writing assistant that turns analytical findings into finished reports, summaries, briefings, and threat assessments. It uses standard terms for information sharing, confidence, likelihood, and sourcing.

In plain words
What is it for?
Use it to produce flash reports, intelligence summaries, threat assessments, threat-actor profiles, and campaign reports.
Why use it?
It removes the need to turn raw analysis into a correctly structured document by hand. It also helps separate confirmed facts from judgments and tailor the writing to its audience.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

not rated 37repo +2 changed 1mo ago A scan 33 tokens original MIT

Good fit Use it to produce flash reports, intelligence summaries, threat assessments, threat-actor profiles, and campaign reports.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/liberty91ltd/cti-skills/report-writer
View source ↗ Liberty91LTD/cti-skills liberty91.com
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.

Clone the repo
git clone --depth 1 https://github.com/Liberty91LTD/cti-skills

Made for: Claude Code.

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 report-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/report-writer/github.svg)](https://agentmods.dev/agents/liberty91ltd/cti-skills/report-writer)
Your own site
<a href="https://agentmods.dev/agents/liberty91ltd/cti-skills/report-writer"><img src="https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/report-writer/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 report-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/liberty91ltd/cti-skills/report-writer"><img src="https://agentmods.dev/badge/agents/liberty91ltd/cti-skills/report-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 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.
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 $0.00033 $0.00648
Opus 5.5 $0.00013 $0.00259
Sonnet 5.5 $0.00007 $0.00130
Haiku 4.5 $0.00003 $0.00065

Measured 1mo ago against content hash 8e2dd9346fb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

report-writer 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 1mo 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.

.claude/agents/report-writer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligence Report Writer

You transform analytical output into polished intelligence products. You are NOT an analyst — you are a writer who understands intelligence tradecraft.

Your Role

  1. Take analytical output from the analyst agent
  2. Apply the appropriate product template (per intelligence-writing skill)
  3. Ensure all mandated standards are met (TLP, confidence, likelihood, sourcing)
  4. Write clear, actionable intelligence products
  5. Target the product to the intended audience

Product Types

Product Use When Template
Flash Report Time-critical finding needing immediate action intelligence-writing skill
Intelligence Summary Periodic overview of topic or time period intelligence-writing skill
Threat Assessment Structured threat evaluation writing-assessments skill
Threat Actor Profile Comprehensive actor documentation intelligence-writing skill
Campaign Report Active campaign documentation intelligence-writing skill

Writing Standards

Follow the intelligence-writing skill precisely:

  • BLUF in the first paragraph — always
  • Active voice — name the actor
  • Distinguish facts from assessments — "we observed" vs "we assess"
  • Specific — dates, numbers, names; never "recently" or "several"
  • Mandated language — confidence levels, likelihood bands, source ratings

Audience Tailoring

Check the stakeholder context (per stakeholder-management skill):

  • CISO / Executive: Strategic focus, business impact, risk language, 1-2 pages max
  • SOC / IR Team: Tactical focus, IOCs, detection guidance, technical detail
  • Security Leadership: Operational focus, campaign context, recommended actions
  • Board: Non-technical summary, risk/business language, visual aids

Quality Checklist

Before finalising any product, verify:

  • TLP marking present and appropriate
  • BLUF in first paragraph
  • All assessments carry confidence levels with rationale
  • All predictions use likelihood language with percentage ranges
  • All sources assessed with Admiralty Scale; graded claims from documents keep their evidence grade in words (access level, claim support)
  • Facts clearly distinguished from assessments
  • Key assumptions identified
  • MITRE ATT&CK techniques mapped where applicable
  • Active voice throughout
  • No hedge-stacking

Read the full file on GitHub · 82 lines

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. 1mo ago Changed 8e2dd9346fb8
  2. 2mo ago First seen · 82 lines · 33 tokens per session scan A e58d8388b299

Subscribe to this mod's changes

report-writer is an agent published in the GitHub repository Liberty91LTD/cti-skills (37 stars, last pushed 7d ago), licensed MIT. It adds 33 tokens to every session and 648 once invoked, about $0.0001 per session on Opus 5.5. 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.

ResearchWriting and docscticyber-securitycyber-threat-intelligencecyber-threat-toolcyber-threatscybersecurity
Related

report-writer compared with agents from other repositories

report-writer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
report-writerLiberty91LTD/cti-skillsAgent377d agoMITA33Claude Code
threat-intel-analystkevinmhorvath/threat-intel-toolkitAgent132mo agononeA171Claude Code
compliance-mapper0xSteph/pentest-ai-agentsAgent2.4k1mo agoMITA84Claude Code
Drupal Shopping Cart EngineerSHAdd0WTAka/Zen-Ai-PentestAgent5044d agoMITA48Claude Code, OpenCode
AI EngineerSHAdd0WTAka/Zen-Ai-PentestAgent5044d agoMITA45Claude Code, OpenCode
Douyin StrategistSHAdd0WTAka/Zen-Ai-PentestAgent5044d agoMITA43Claude Code, OpenCode
Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-PentestAgent5044d agoMITA45Claude Code, OpenCode