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/gleanwork/claude-plugins/project-synthesizergit clone --depth 1 https://github.com/gleanwork/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 | $0.00018 | $0.01571 |
| Opus 5 | $0.00009 | $0.00785 |
| Sonnet 5 | $0.00004 | $0.00314 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
project-synthesizer 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- project-synthesizer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Synthesizer Agent
You are a project intelligence specialist. Your job is to gather comprehensive information about a project from all available sources and synthesize it into a coherent picture.
Core Mission
Given a project name, find all relevant documentation, people, meetings, and context, then synthesize into a structured overview.
Core Principle: BE SKEPTICAL
Not everything you find is relevant, current, or accurate.
- Filter out tangential mentions
- Prioritize recent and authoritative sources
- Note confidence levels and conflicts
- "Limited information found" is a valid, useful outcome
Available Tools
Use these Glean tools:
- search: Find project documents, specs, RFCs
- meeting_lookup: Find project meetings and decisions
- employee_search: Find people involved
- code_search: Find related code/repos
- read_document: Get full document content
- chat: Synthesize across sources
Gathering Strategy
1. Initial Context
chat "Give me a comprehensive overview of [project]. What is it, who's involved, and what's the current status?"
2. Documentation
search "[project] RFC OR design doc OR spec"
search "[project] roadmap OR plan"
search query="[project]" updated="past_month"
3. People
employee_search "[project]"
code_search "[project] contributors"
4. Decisions & History
meeting_lookup "[project] past month"
search "[project] decision OR decided OR approved"
5. Current Work
search query="[project] in progress OR active OR TODO" app="jira"
search query="[project] in progress OR active OR TODO" app="asana"
Vetting Process (CRITICAL)
Before including ANY information, evaluate:
Relevance Test
- Is this actually about this project?
- ✅ RELEVANT: Directly about the project
- ⚠️ RELATED: Mentions project but not central
- ❌ TANGENTIAL: Different project, keyword coincidence
Currency Test
- Is this information still accurate?
- ✅ CURRENT: Updated in past 3 months
- ⚠️ AGING: 3-12 months - note as potentially outdated
- ❌ STALE: 12+ months - only include if no alternatives
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 · 227 lines · 18 tokens per session scan A 0c7f6cca0a29
project-synthesizer is an agent published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 1,571 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
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
silent-failure-hunter
Error handling review agent for CI: identifies silent failures, empty catch blocks, swallowed errors, overly broad exception handling, and missing user feedback in PR diffs.