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.
npx skills add organvm-iv-taxis/a-i--skills --skill claude-project-manifestgit clone --depth 1 https://github.com/organvm-iv-taxis/a-i--skillsWrote 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.
[](https://agentmods.dev/skills/organvm-iv-taxis/a-i--skills/claude-project-manifest)<a href="https://agentmods.dev/skills/organvm-iv-taxis/a-i--skills/claude-project-manifest"><img src="https://agentmods.dev/badge/skills/organvm-iv-taxis/a-i--skills/claude-project-manifest/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.
<a href="https://agentmods.dev/skills/organvm-iv-taxis/a-i--skills/claude-project-manifest"><img src="https://agentmods.dev/badge/skills/organvm-iv-taxis/a-i--skills/claude-project-manifest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01365 |
| Opus 5 | $0.00025 | $0.00682 |
| Sonnet 5 | $0.00010 | $0.00273 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
claude-project-manifest 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Project Manifest
Create structured, annotated documentation of Claude projects that tracks files, conversation threads, and their relationships.
When to Use
- Documenting project contents and structure
- Creating file inventories with annotations
- Tracking conversation history across sessions
- Building navigable knowledge maps
- Onboarding new collaborators to existing projects
Core Concepts
Manifest Structure
A manifest has four primary sections:
- Metadata: Project-level information (ID, version, status)
- Files: Annotated file inventory with provenance
- Threads: Conversation summaries and accomplishments
- Relations: Dependencies and connections between entities
ID System
| Entity | Format | Example |
|---|---|---|
| Project | PROJ-{YEAR}-{SEQ} |
PROJ-2024-001 |
| File | FILE-{SEQ} |
FILE-042 |
| Thread | THR-{SEQ} |
THR-017 |
| Relation | REL-{SEQ} |
REL-123 |
Quick Start
Minimal Manifest
manifest:
id: "PROJ-2024-001"
version: "1.0.0"
created: "2024-01-15T10:30:00Z"
project:
name: "My Project"
description: "Brief description of the project"
status: active
files:
- id: "FILE-001"
path: "src/main.py"
title: "Main Entry Point"
summary: "Application entry and initialization"
Full File Entry
files:
- id: "FILE-001"
path: "src/main.py"
type: source # source | config | doc | asset | generated
thread_id: "THR-001"
title: "Main Entry Point"
summary: "One-line description of purpose"
notes: |
Extended annotation explaining:
- Design decisions made
- Why this approach was chosen
- Key implementation details
- Known limitations or TODOs
tags: [core, initialization]
depends_on: ["FILE-002", "FILE-003"]
created: "2024-01-15T10:30:00Z"
modified: "2024-01-16T14:20:00Z"
Thread Entry
threads:
- id: "THR-001"
started: "2024-01-15T10:30:00Z"
ended: "2024-01-15T12:45:00Z"
title: "Initial Project Setup"
summary: "Created core infrastructure and configuration"
accomplishments:
- "Created directory structure"
- "Implemented Config class with validation"
- "Added logging infrastructure"
files_created: ["FILE-001", "FILE-002"]
files_modified: []
decisions:
- "Chose YAML over JSON for config readability"
- "Used dataclasses instead of Pydantic for simplicity"
tags: [setup, infrastructure]
What ships with it
7 files 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.
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.
- 12d ago First seen · 208 lines · 50 tokens per session scan A 76b85a650d58
claude-project-manifest is a skill published in the GitHub repository organvm-iv-taxis/a-i--skills (17 stars, last pushed 16d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,365 once invoked, about $0.0003 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.
Other skills, from other repositories
supersede-outdated-docs
Use when a curated-knowledge unit turns out to be wrong, outdated, or replaced by better evidence. Triggers on requests like "correct kb-0003", "update this finding, it changed", "this knowledge unit is no longer true", or "supersede X with Y". Never use this to justify editing a unit's frontmatter or body in place.
obsidian-docs
Create comprehensive technical documentation following Obsidian conventions with bidirectional linking, proper folder structure, templates, and developer-focused content. Use when creating documentation, READMEs, wikis, knowledge bases, ADRs, runbooks, or any technical writing. Triggers on: documentation, docs…
write-ops-runbook
Use when documenting a repeatable operational procedure that on-call engineers or operators must execute under pressure.
Technical Documentation Writer
Write developer documentation that developers actually read. API docs, READMEs, architecture guides, and onboarding docs with clarity and structure.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
document-skills
Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the most specific document skill to reduce noise and improve routing precision.