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/commands/synaptiai/synapti-marketplace/verify)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/verify"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/verify.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 | $0.00020 | $0.01654 |
| Opus 5 | $0.00010 | $0.00827 |
| Sonnet 5 | $0.00004 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
verify 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Claims
Verify factual claims in content using deep research methodology. Can be run standalone or after NCI analysis.
Context Isolation: This command uses the
claim-verifieragent which auto-loads both theconducting-deep-researchandnci-manipulation-analysisskills. Verification happens in a forked context, allowing multiple claims to be researched without polluting the main conversation.
Usage
/decipon:verify <URL or text content>
/decipon:verify --claims "claim1" "claim2" "claim3"
Arguments
$ARGUMENTS: Content to analyze OR specific claims to verify- Content: URL, file path, or text
--claims: Verify specific claims directly
Purpose
Fact-check key claims using deep research:
- Extract factual assertions from content
- Research each claim using multiple sources
- Score source reliability (1-100 confidence)
- Track contradictions and agreements
- Report verification status with evidence
Workflow
-
Extract Claims (if content provided)
- Identify factual assertions
- Prioritize by impact (Critical/High/Medium/Low)
- Focus on verifiable claims (not opinions)
-
Research Each Claim
- Apply deep research methodology
- Search for supporting/contradicting evidence
- Evaluate source quality
- Track agreements and contradictions
-
Evaluate Sources
- Score confidence (1-100)
- Note source type and potential bias
- Check for corroboration
-
Generate Report
- Verification status per claim
- Source citations with confidence
- Overall credibility assessment
Verification Statuses
| Status | Meaning |
|---|---|
| VERIFIED | 2+ high-confidence sources support claim |
| PARTIALLY VERIFIED | Core claim true but with caveats |
| UNVERIFIED | Cannot find supporting evidence |
| CONTRADICTED | High-confidence sources refute claim |
Output Format
═══════════════════════════════════════════════════
CLAIM VERIFICATION REPORT
═══════════════════════════════════════════════════
SUMMARY
───────
Claims Analyzed: [N]
✓ Verified: [N]
~ Partial: [N]
? Unverified: [N]
✗ Contradicted: [N]
DETAILED FINDINGS
─────────────────
CLAIM 1: "[Statement]"
Status: [STATUS]
Confidence: [%]
Sources:
[1] example.com (Confidence: 85) - Supports
[2] reuters.com (Confidence: 90) - Supports
Finding: [What research revealed]
───────────────────────────────────────────────────
CLAIM 2: "[Statement]"
[Continue for each claim...]
═══════════════════════════════════════════════════
METHODOLOGY
Applied deep research verification protocol
Consulted [N] sources total
Source confidence scoring: 1-100 scale
RECOMMENDATIONS
[Any suggested follow-up verification]
═══════════════════════════════════════════════════
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 · 251 lines · 20 tokens per session scan A 8e4e967c0dfe
verify is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,654 once invoked, about $0.0001 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 commands, from other repositories
create-worktree
Follow these steps to create a git worktree.
paper-trail-review
Review and arbitrate problematic references (cascade-exhausted, unresolved UID, awaiting OCR). Generates an up-to-date report, walks through cases by category, and applies arbitration decisions to the registry.
paper-trail-decide
Inspect a single reference in detail (identity, PDF status, acquisition history with verdicts, citation context in vault, state transitions) and decide its fate. Offers actionable decisions based on the ref's current state.
paper-trail-new-paper
Start writing an academic paper (IMRaD structure) on a topic, with anti-hallucination citation verification at every step. Builds on existing audited SOTAs.
paper-trail-registry-cleanup
Nettoyage historique du registre des fiches bibliographiques (les 900 fiches existantes). Cible les vieilles fiches mal nommées (0000, untitled) ET les duplicates avec suffixes numériques (foo2020bar2, 234) qui sont des artefacts de runs INGEST passés. Délègue les décisions au sub-agent textbook-resolver. Les merge…
paper-trail-cascade
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy on each download.