dossier

A documented engineering workflow stored in one DOSSIER.md file. It organizes dependent tasks, records rules that must remain true, tracks changes across repositories, logs progress, and uses investigator and reviewer agents.

In plain words
What is it for?
Use it to plan multi-step changes, track work across repositories, investigate failures, check code drift, and review changes before committing. TDD, one of its listed keywords, means writing tests before or alongside the code they check.
Why use it?
It keeps longer development work organized and resumable, while helping detect when the code or plan has drifted from the intended design.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add raisedadead/claude-code-plugins
agentmods
npx agentmods add plugins/raisedadead/claude-code-plugins/dossier
Clone the repo
git clone --depth 1 https://github.com/raisedadead/claude-code-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

dossier 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 yesterday.

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/dossier/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "dossier",
  "description": "Engineering workflow in one resumable DOSSIER.md: dependency-ordered tasks, invariants, drift detection, cross-repo state, a rolling status log, and scout + reviewer subagents.",
  "author": {
    "name": "Mrugesh Mohapatra",
    "email": "[email protected]",
    "url": "https://github.com/raisedadead"
  },
  "homepage": "https://github.com/raisedadead/claude-code-plugins",
  "repository": "https://github.com/raisedadead/claude-code-plugins",
  "license": "ISC",
  "keywords": [
    "dossier",
    "spec-driven",
    "tdd",
    "workflow",
    "scratchpad",
    "phase"
  ]
}
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. yesterday First seen · 22 lines scan A 12771c86e72c

Subscribe to this mod's changes

dossier is a plugin published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.