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 skills add synaptiai/synapti-marketplace --skill verification-protocolgit 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/skills/synaptiai/synapti-marketplace/verification-protocol)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/verification-protocol"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/verification-protocol/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/skills/synaptiai/synapti-marketplace/verification-protocol"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/verification-protocol.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 | $0.00136 | $0.01923 |
| Opus 5 | $0.00068 | $0.00962 |
| Sonnet 5 | $0.00027 | $0.00385 |
| Haiku 4.5 | $0.00014 | $0.00192 |
Grade A, and why
verification-protocol 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Protocol
One independent pass. Owns falsification, sampling, tracing, and finding emission — and deliberately owns none of the merge, the repair, or the round loop.
Iron Law
VERIFY BY ATTEMPTING TO FALSIFY. Start from the sources, not from the document — and never read another pass's findings.
A pass that opens the package, reads a claim, and finds it plausible has produced nothing. The only output that counts is a check that could have failed.
The independence contract
You do not receive, and must not seek out: the drafting transcript · the authored project-model narrative as authority · another pass's findings · prior-round findings · the reconciliation logic · the author's self-score.
You receive: the package root · the resolved scope · the source roots · your lens · the round number.
This is not etiquette. Passes that share context converge on each other's blind spots, which defeats the entire reason there are three of them. If you find yourself reasoning about "what the other passes probably caught", stop — that reasoning is the failure mode.
Full contract, enforcement mechanisms, and the two independence tiers: references/independent-audit-protocol.md.
Your lens
| Pass | Lens | Emphasis |
|---|---|---|
| A | Evidence and coverage | Rebuild the inventory from the contracts. Audit the census categories at 100%. Verify sampled claims against cited rows and the original source |
| B | Model falsification | Execute end-to-end traces from the sources. Report every point where the package and reality diverge |
| C | Audience, consistency, disclosure | Simulate each reader completing their task using only the package. Then headers, dates, links, terminology, leakage |
Run your lens. Do not compensate for what you imagine another pass is missing.
Step order
- Independent coverage. Inventory the project evidence yourself. Compare against the index, ledger, terminology, registers. Rebuild the required-file list from
references/package-contract-*.md, never from the documentation index — auditing the index against itself proves nothing. - Claim sample. Stratum 1 is a census of the categories in
verification.claimSample.auditAllCategories— security, compliance, licensing, financial, performance, customer-reference — audited at 100%. Stratum 2 is a risk-based sample of the rest. State the method and size; an unstated sample is not evidence. - Falsify the model. Execute the traces. See below.
- Audience usability. Simulate the readers for your lens.
- Mechanics. Links, diagram syntax versus inventories, examples against schemas, referenced versions, accidental secrets, duplicated facts across documents.
- Findings before repair. Emit the table. Do not edit anything first.
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 · 123 lines · 136 tokens per session scan A 7a1f35cc8aef
verification-protocol is a skill published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 136 tokens to every session and 1,923 once invoked, about $0.0007 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 skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
pipeline-efficiency-benchmark
A repeatable benchmark for comparing different versions of a development pipeline. It runs the same public tasks in isolated workspaces and records scores, tokens, time, tool calls, and cost.
x-qdev
A compact development workflow for a small, clearly defined code change. It keeps the requirement, initially failing tests, implementation, and real verification results in one task document, following TDD, or test-driven development.
x-adversarial-risk
A focused adversarial review of a software specification. It tries to find small counterexamples that would expose incorrect implementations, such as invalid state changes, crashes, duplicate actions, permission mistakes, or concurrent events.
x-qa-gate
A quality-review gate for completed development tasks. It checks the code against the request, design, tests, verification evidence, and current changes, using different review rounds for different risk levels.