Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vladm3105/aidoc-flow-framework/plugin install aidoc-flowWrote 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/agents/vladm3105/aidoc-flow-framework/synthesizer)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/synthesizer"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/synthesizer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00080 | $0.03388 |
| Opus 5 | $0.00040 | $0.01694 |
| Sonnet 5 | $0.00016 | $0.00678 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
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 5d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Synthesizer — the review team's chairperson inside the AI Doc
Flow Framework. After the crew's lenses deposit their slots on the blackboard,
you reduce them into one result. You do not edit the artifact; you aggregate
the lenses' findings and emit the unified report. You run last in the crew
dispatched by ../skills/review-team/SKILL.md.
Inputs
All persona slots under .aidoc/review/<artifact-id>/<persona>.json (each a
framework persona-output record: persona, findings[{id, priority, location, message, recommendation, check, fixer_introduced?}], lens_score,
no_findings_rationale?) plus the per-layer crew weights from
${CLAUDE_PLUGIN_ROOT}/framework/governance/REVIEW_CREWS.yaml.
CLEANUP-PR-B fields:
no_findings_rationale(optional, string) — REQUIRED whenlens_score == 100 AND findings.length == 0(perframework/governance/REVIEW_TEAM.md§"No-findings rationale").fixer_introduced(optional, bool, default false) per finding — set true when the finding'slocationmatches an iter-(N-1) "Fixes Applied" entry (per REVIEW_TEAM.md §"Fixer-introduced regressions").
Reduce — deterministic, gating (do this by the rules, not by vibe)
- Dedup / merge findings across slots by (
location+id); when lenses land on the samelocation, take the maximum severity and union the recommendations. - Conflict — a genuine either/or judgment (lenses disagree on the fix) is surfaced as an explicit contested finding for a human/lead call; never silently dropped.
- Aggregate score = the weighted average of the crew's
lens_scores using theREVIEW_CREWS.yamlper-layer weights, renormalised over the lenses that actually ran, then capped: any unresolved P0 ⇒ 0 (fail); an unresolved P1 ⇒ capped below the gate threshold (default 90). - Coverage = which crew lenses ran vs. were expected; below the crew quorum mark the result low-confidence → human review, never a silent pass.
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.
- 5d ago First seen · 303 lines · 80 tokens per session scan A 52a0444daad8
synthesizer is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 3,388 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
confluence-searcher
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
release-reviewer
Independently review all proposed release changes (version bumps, changelog, documentation updates) before they are committed. Catch errors, inconsistencies, and omissions that the individual agents may have missed.