What is trailtool CLAUDE.md?

A project guide for Claude Code, containing trailtool's context, build and test commands, release steps and folder layout.

Helping the agent develop, test, release and navigate the trailtool codebase.

It gives the coding agent repository-specific instructions instead of making it infer how the project works.

How engseclabs/trailtool configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to engseclabs/trailtool. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/engseclabs/trailtool/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/engseclabs/trailtool

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/engseclabs/trailtool/claude-md/github.svg)](https://agentmods.dev/instructions/engseclabs/trailtool/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/engseclabs/trailtool/claude-md"><img src="https://agentmods.dev/badge/instructions/engseclabs/trailtool/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/engseclabs/trailtool/claude-md"><img src="https://agentmods.dev/badge/instructions/engseclabs/trailtool/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,035 This file is loaded in full into every session.

When invoked 1,035 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01035	$0.01035
Opus 5.5	$0.00414	$0.00414
Sonnet 5.5	$0.00207	$0.00207
Haiku 4.5	$0.00103	$0.00103

Measured 7d ago against content hash b646a1e92bff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trailtool CLAUDE.md 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 7d 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.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TrailTool

Go CLI for querying precomputed CloudTrail data. Entrypoint: cmd/trailtool/main.go.

Build & Test

go build ./cmd/trailtool/          # build
go test ./...                      # test
AWS_PROFILE=sandbox-admin AWS_REGION=us-east-1 go run ./cmd/trailtool/ status  # smoke test

Releasing

Releases are automated via goreleaser + GitHub Actions. Pushing a semver tag triggers the workflow.

git tag v0.X.0
git push origin v0.X.0

This will:

Build linux/darwin binaries (amd64 + arm64)
Create a GitHub release with archives
Update the Homebrew tap (engseclabs/homebrew-tap)
Publish the ingestor and both forwarders to the Serverless Application Repository (see below)

Users install/upgrade via brew install engseclabs/tap/trailtool.

Config: .goreleaser.yaml, .github/workflows/release.yaml.

Serverless Application Repository

The same tag publishes ingestor/template.yaml as trailtool-ingestor, ingestor/template-forwarder.yaml as trailtool-cloudtrail-forwarder, and ingestor/template-otlp-forwarder.yaml as trailtool-otlp-forwarder to the AWS Serverless Application Repository (account 843363563907), so consumers can nest them with AWS::Serverless::Application. Each SAR listing lives in its template's Metadata: AWS::ServerlessRepo::Application block. Each gets the tag's version with the v stripped (v1.2.0 → 1.2.0). SAR versions are immutable, so publish-sar skips a version that already exists, which makes a failed job safe to re-run. sar-public sets each application policy to Principals='*', which is what makes it publicly listed.

The serverless-app-repo job is skipped unless these repository variables are set (Settings → Secrets and variables → Actions → Variables), so tags keep working in forks and before SAR is configured:

Variable	Purpose
`SAR_S3_BUCKET`	Bucket holding the packaged artifacts. Its policy must let `serverlessrepo.amazonaws.com` read it — `make -C ingestor sar-bucket-policy SAR_BUCKET=…` prints the statement.
`SAR_PUBLISH_ROLE_ARN`	Role assumed through GitHub OIDC. Needs `s3:PutObject` on that bucket plus `serverlessrepo:CreateApplication`, `serverlessrepo:CreateApplicationVersion`, `serverlessrepo:UpdateApplication`, `serverlessrepo:ListApplicationVersions` and `serverlessrepo:PutApplicationPolicy`.
`SAR_REGION`	Optional; defaults to `us-east-1`.

Read the full file on GitHub · 90 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.

7d ago Changed · +1 lines · +34 tokens per session b646a1e92bff
12d ago Changed · +1 lines · +35 tokens per session 81e7cded8909
13d ago Changed · +31 lines · +425 tokens per session 550476fdf90d
2mo ago First seen · 57 lines · 541 tokens per session scan A 6e8e81c65162

Subscribe to this mod's changes

trailtool CLAUDE.md is an instructions file published in the GitHub repository engseclabs/trailtool (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,035 tokens to every session, about $0.0041 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.

trailtool CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
trailtool CLAUDE.mdengseclabs/trailtool	Instructions file	45	7d ago	Apache-2.0	A	1,035	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

trailtool: Instructions file for Claude Code