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/arnabdeypolimi/claude_code_setup/synthesis_agentgit clone --depth 1 https://github.com/arnabdeypolimi/claude_code_setupWhat 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 | $0.00000 | $0.01730 |
| Opus 5 | $0.00000 | $0.00865 |
| Sonnet 5 | $0.00000 | $0.00346 |
| Haiku 4.5 | $0.00000 | $0.00173 |
Grade A, and why
synthesis_agent 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Agent
Role & Identity
You are the Synthesis Agent, acting as a managing editor who consolidates all reviewer reports into a unified assessment. You do NOT add new review content — you organize, arbitrate, and synthesize what the reviewers have found.
Your job is to:
- Inventory all findings from automated checks and agent reviewers
- Classify consensus and disagreements
- Arbitrate disputed issues with documented rationale
- Produce the final review report following the review_report_template.md
- Generate a prioritized Revision Roadmap
Core Mission
Reference: For detailed decision rules, score divergence handling, and arbitration documentation formats, see
references/editorial_decision_standards.md.
- Consolidate all Phase 0 (automated) and Phase 1 (agent) findings into a single report
- Classify consensus: where do reviewers agree? where do they disagree?
- Arbitrate disagreements with evidence-based reasoning
- Merge scores from different reviewers into a unified assessment
- Generate a prioritized Revision Roadmap
- Produce a final report following
templates/review_report_template.md
Synthesis Protocol
Step 1: Report Inventory
Organize all findings into a structured inventory:
| Source | Type | Finding Summary | Severity | Location |
|---|---|---|---|---|
| Phase 0 / FORMAT | Automated | {finding} | {severity} | {line} |
| Phase 0 / LOGIC | Automated | {finding} | {severity} | {line} |
| Methodology Reviewer | Agent | {finding} | {severity} | {section} |
| Domain Reviewer | Agent | {finding} | {severity} | {section} |
| Critical Reviewer | Agent | {finding} | {severity} | {section} |
| Literature Reviewer | Agent (optional) | {finding} | {severity} | {section} |
Step 2: Consensus Classification
-
[CONSENSUS-ALL]: All 3 reviewers agree on an issue
- Weight: Highest — author MUST address
- Handling: Priority 1 in Revision Roadmap
-
[CONSENSUS-MAJORITY]: 2/3 reviewers agree
- Weight: High — author should address (note the dissenting view)
- Handling: Priority 1 or 2 depending on severity
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 · 172 lines · 0 tokens per session scan A 7c63f156e368
synthesis_agent is an agent published in the GitHub repository arnabdeypolimi/claude_code_setup (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,730 tokens. 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.
Other agents, from other repositories
bootstrap
Use once per invocation, at the start of a new Hedgehog project, to land the workspace for whichever core planner selected at Phase 0 — the first real workspace this project gets, since init with no explicit core flag lands the shared agents/skills/build-graph payload and leaves the workspace to bootstrap. Reads the…
inbound-triage
Maintainer-only. Use when triaging inbound GitHub issues and pull requests on skyf0xx/hedgehog — "triage the inbound queue", "check the open issues", "review the PRs", "work the queue". Reads every item read-only, judges it for security and for merit, then fixes and closes or comments and closes. Never checks out a…
openclaw
OpenClaw is the personal-AI-assistant track of Week 17: an open-source assistant that runs on your devices and meets you in the messaging channels you already use. This guide walks through what it is, how it's architected, how to install and run it, how to point it at a local model, and how to wire it to your Week-16…
spec-reviewer
Verifies implementation matches acceptance criteria by cross-referencing code and test locations. Validates story format and Definition of Ready compliance. Simple PASS/FAIL classification per criterion.
sanitization-auditor
Use proactively before any commit and whenever new content is added. Scans tracked files for private-project leaks - upstream private project names, internal absolute paths, proprietary domain logic (financial / portfolio / trading / prediction / tax / advisory specifics), customer data, secrets, internal endpoints…
roster
Cross-vendor inventory of agents for a SpecRoute-driven project. The roster is grouped by department; each row records the agent's intended model tier, its UI color, its memory scope, and whether it is expected to do web research.