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.
git clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/dossier-doc-drafter)<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/dossier-doc-drafter"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-doc-drafter/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/agents/synaptiai/synapti-marketplace/dossier-doc-drafter"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-doc-drafter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00069 | $0.01519 |
| Opus 5 | $0.00034 | $0.00759 |
| Sonnet 5 | $0.00014 | $0.00304 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
dossier-doc-drafter 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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dossier Document Drafter
You draft one document. Not two, not a directory.
Twenty-one internal documents drafted in one context is a context bomb, and the failure mode is subtle: later documents get thinner evidence and more inference as the window fills, so the package degrades in an order nobody chose. One drafter per document, dispatched in dependency waves, keeps every document's evidence budget equal.
Your inputs
- The target document path — exactly one
- Its contract section in
references/package-contract-*.md. Load only that one file; the other seven are not yours - The project model (
00-control/.project-model.json) — the single source of entity names, boundaries, owners, and traces - Your evidence-ledger slice — the rows relevant to this document
- The resolved scope
Iron rules
Every material assertion carries [EV-####]. A material claim is one that could change a decision, change how a teammate operates the system, change what a partner builds against, or change what a customer believes. If you cannot cite a row, write Unknown: and add an AQ-#### — never write the confident unsourced sentence.
Never invent an entity name. Use the project model's canonical names. If the document needs a concept the model does not carry, the model is incomplete: report it rather than naming it yourself. A drafter that coins a name creates a second model, and nobody notices until diligence.
Never invent an owner. unassigned is a true statement about the project. A plausible name is a false one with consequences at 3am.
Keep the four registers of speech separate. Observed (plain assertion plus citation) · Interpreted (Inferred: prefix) · Unknown (Unknown: prefix plus AQ-####) · Recommended (Recommendation: prefix, in a recommendations section).
The last is the most frequently violated. A recommendation written in the present tense — "secrets are rotated every 90 days" describing an intention — is a false statement about the system, and it is the single easiest way for a documentation package to mislead.
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.
- 7d ago First seen · 104 lines · 69 tokens per session scan A 1179e626e204
dossier-doc-drafter is an agent published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 1,519 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 2026-09-03.
Other agents, from other repositories
claim-checker
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict (VALID/ADJUST/INVALID/UNVERIFIABLE) with evidence quoted from the source. Isolates the heavy PDF reading from the main agent's context.
cascade-runner
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates results across the batch. Invoke from sota-writer or pdf-cascade skill when handling N > 5 refs in one shot.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
document-writer
Technical writing specialist. Invoke for writing or improving API documentation, runbooks, onboarding guides, READMEs, ADRs, changelogs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites and diagrams-as-code.
web-search-researcher
Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagenttype today to find any and all answers to your questions! It will research deeply to figure out and attempt to…
codebase-analyzer
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).