A command that turns approved security findings into customer-review deliverables. It can produce an Excel workbook, an optional PDF, and a manifest recording the files’ chain of custody.

Use it after assessment and review to generate the final workbook, optional audit PDF, and evidence manifest from the approved findings.

It prevents reporting before findings have been approved and keeps an audit trail of how the deliverables were produced. If the operator explicitly skips review, that choice is recorded.

report — Command for coding agents by transilienceai: A command that turns approved security findings into customer-review…

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 commands/transilienceai/communitytools/report

Clone the repo

git clone --depth 1 https://github.com/transilienceai/communitytools

Or install communitytools, the plugin that ships this one along with the rest of its 42 skills, 5 commands, 9 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/transilienceai/communitytools/report.svg)](https://agentmods.dev/commands/transilienceai/communitytools/report)

Your own site

<a href="https://agentmods.dev/commands/transilienceai/communitytools/report"><img src="https://agentmods.dev/badge/commands/transilienceai/communitytools/report.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,238 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	$0.00037	$0.01238
Opus 5	$0.00018	$0.00619
Sonnet 5	$0.00007	$0.00248
Haiku 4.5	$0.00004	$0.00124

Measured 4d ago against content hash d370ca9bc19e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report 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.

skills/firewall-review/reference/commands/report.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/report — Render deliverables

No arguments. Operates on the most recent engagement.

Implementation boundary: this command is a reference workflow. The scripts it names are not shipped in communitytools; confirm an accessible compatible runtime before execution. See ../IMPLEMENTATION_STATUS.md.

What to do

Step 1 — Preflight

Check findings.final.jsonl exists. If not, error: "run /launch first".
Check feedback.jsonl exists and has at least one "decision":"approve" entry.
- If missing AND the operator has explicitly requested the report without running /review (e.g. asked for "the report now" / "skip review, render"), synthesize a batch-approve feedback.jsonl — one entry per finding with decision: "approve", decided_by: <engagement.lead_assessor>, mode: "batch-approve-at-report", and reason noting that interactive review was skipped by operator choice. This preserves the audit trail (the mode field makes the path explicit) and satisfies the /report gate. Print a one-line notice in chat so the operator sees it: "Synthesized batch-approve feedback.jsonl; audit trail records mode: batch-approve-at-report."
- If missing AND the operator did NOT ask to skip /review, error: "run /review and approve at least one finding first".
Verify scoping-questionnaire.yaml has non-empty engagement.client, engagement.lead_assessor, and regulatory_overlay. If any are empty, ASK the operator to fill them before rendering — these fields appear on the PDF cover page and in the appendix.

Step 2 — Render deliverables

Run:

python3.11 scripts/render-pdf.py <engagement-dir>
python3.11 scripts/render-xlsx.py <engagement-dir>

These write:

deliverables/report.pdf (10-section canonical audit layout; record the actual rendered page count)
deliverables/remediation-tracker.xlsx (current base renderer: 28-column Findings & Action Plan plus 5 supporting tabs)
deliverables/manifest.json (chain-of-custody: tool/skill versions + input SHA256s + engagement metadata)

Read the full file on GitHub · 79 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.

4d ago First seen · 79 lines · 37 tokens per session scan A d370ca9bc19e

Subscribe to this mod's changes

report is a command published in the GitHub repository transilienceai/communitytools (507 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,238 once invoked, about $0.0002 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.

Code review Documents Security bounty-hunters hackerone pentest pentest-tool security-research

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens

develop-image-prompt.eval

Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.

davistroy/claude-marketplace · 0 tokens

report