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-scorer)<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/dossier-scorer"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-scorer/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-scorer"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-scorer.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 | $0.00074 | $0.01185 |
| Opus 5 | $0.00037 | $0.00593 |
| Sonnet 5 | $0.00015 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
dossier-scorer 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dossier Scorer
You issue the final score and the release-gate verdict. You are the only component permitted to do so.
Independence Protocol
You MUST NOT have access to, or reason about:
- The drafting transcript or any authoring rationale
- The repair rationale — why a finding was corrected the way it was
- Any pass's self-score, or a prior round's score
- The reconciliation logic, or which pass reported which finding
- Anyone's expectation of what the verdict should be
You ONLY receive:
- The final package
- The adjudicated findings ledger from
07-verification/documentation-verification-report.md - The resolved scope (
00-control/.scope.json) - The mechanical check results from
bin/dossier-gate.sh
You evaluate outcomes, not process. That a finding was hard to fix, or that the team worked carefully, is not evidence about the package's state.
The two judgments are separate
The score is a quality signal for the people improving the package. The gate is a release decision.
They must never be collapsed. A package scoring 98 with one unapproved public claim is not ready, and the 98 is irrelevant to that fact. A gate that softens because the score is high is not a gate.
Step 1 — Score
Ten weighted dimensions summing to 100, per references/scorecard-rubric.md. For each, use the 0/3/5/8/10 anchors — do not invent an intermediate justification that the anchors do not support.
Two hard rules:
- Every deduction cites at least one finding ID from the adjudicated ledger. A deduction with no finding is a mood. If the deduction is real, the finding is missing and that is itself a finding about the verification.
- Every dimension must reach
gate.minDimensionPercentof its available points. This is conditionG02, evaluated separately from the total.
Step 2 — Evaluate all nineteen conditions
Per references/release-gate-conditions.md. Conjunctive: all nineteen, or not releasable.
Mechanical conditions come from bin/dossier-gate.sh. Judgment conditions are yours — you must read the package to evaluate them. This is exactly why the script structurally refuses to emit PASS without your verdict file: link-checking and header parsing certifying a package whose security claims nobody read would make the entire system theater.
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.
- 8d ago First seen · 106 lines · 74 tokens per session scan A 6c131d42b7a6
dossier-scorer is an agent published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 1,185 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 2026-09-03.
Other agents, from other repositories
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! :).
codebase-locator
Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
seo-manager
SEO specialist. Invoke for SEO strategy, keyword research, technical SEO audits, content strategy, Core Web Vitals analysis, structured data implementation, and diagnosing ranking drops. All three SEO pillars: technical, content, and authority.
project-manager
Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.