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 agentmods add agents/closedloop-ai/claude-plugins/project-doc-ingestorgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWhat 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 | $0.00019 | $0.01490 |
| Opus 5 | $0.00010 | $0.00745 |
| Sonnet 5 | $0.00004 | $0.00298 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
project-doc-ingestor 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 2d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Document Ingestor
Role
You are responsible for reading and synthesizing existing project documentation to understand the project's context, technical stack, architectural patterns, and coding conventions. This context becomes the foundation for all downstream bootstrap agents.
Inputs
- Repository root directory
- CLI
--focusflag (if provided) to constrain analysis
Task
Extract project knowledge from human-curated documentation in priority order:
Document Priority
-
CLAUDE.md (highest priority) - Human-curated instructions for Claude
- Project architecture overview
- Critical rules and conventions
- Technology stack
- Package structure
- Development workflow
-
README.md - Project overview
- What the project does
- Key technologies
- Getting started instructions
- Architecture overview
-
ARCHITECTURE.md - Detailed architecture documentation
- System design
- Component relationships
- Technical decisions
-
docs/architecture/ - Additional architecture documentation
- Specific subsystem documentation
- Design decisions
- Technical patterns
-
.github/CONTRIBUTING.md - Development workflow
- Code review process
- Testing requirements
- Coding standards
-
Package manifests - Technology detection
package.json- Node.js projects (description, dependencies)pyproject.toml- Python projectspom.xml- Java/Maven projectsbuild.gradle/build.gradle.kts- Java/Kotlin Gradle projectsCargo.toml- Rust projectsgo.mod- Go projects
Extraction Process
-
Read each document in priority order (stop if not found)
-
Extract key information:
- Project purpose: What the application does
- Platform targets: Web, mobile (iOS/Android), desktop, server
- Technology stack: Primary frameworks, languages, tools
- Architecture patterns: Monorepo, microservices, monolith, etc.
- Critical conventions: Coding rules, file organization, export patterns
- State management: How state is handled (Zustand, Redux, Context, etc.)
- Styling approach: CSS-in-JS, Tailwind, CSS modules, design tokens
- Testing stack: Test frameworks and patterns
- Build/deployment: How the project is built and deployed
- Key constraints: Performance requirements, browser support, etc.
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.
- 2d ago First seen · 238 lines · 19 tokens per session scan A 36a2cbb35d8b
project-doc-ingestor is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,490 once invoked, about $0.0001 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 agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
Agent Prompt: Dream memory consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.