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/cogni-work/insight-waveWrote 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/cogni-work/insight-wave/claims)<a href="https://agentmods.dev/commands/cogni-work/insight-wave/claims"><img src="https://agentmods.dev/badge/commands/cogni-work/insight-wave/claims/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/commands/cogni-work/insight-wave/claims"><img src="https://agentmods.dev/badge/commands/cogni-work/insight-wave/claims.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 | $0.00000 | $0.01339 |
| Opus 5.5 | $0.00000 | $0.00536 |
| Sonnet 5.5 | $0.00000 | $0.00268 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
claims 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 1mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims Command
Manage the full lifecycle of sourced claims: submission, verification against cited sources, dashboard review, source inspection, user-guided resolution, and interactive cobrowsing recovery.
Usage
/claims <mode> [options]
Modes
submit — Ingest new claims
/claims submit "claim statement" --source "https://url" --title "Source Title"
/claims submit --batch (reads claims from context or file)
Submit one or more claims for tracking and future verification.
Required for single claim:
- First argument: the claim statement (quoted)
--source: source URL--title: human-readable source title
Batch mode:
--batch: submit multiple claims from the current conversation context or a provided JSON array- Each batch item needs: statement, source_url, source_title
Processing:
- Parse the claim(s) from arguments
- Invoke the
cogni-workspace:claimsskill with modesubmit - Report how many claims were submitted and their IDs
verify — Run verification pipeline
/claims verify
/claims verify --id claim-abc123
Verify unverified claims against their cited sources. Optionally re-verify a specific claim.
Options:
--id <claim-id>: verify (or re-verify) a specific claim- No options: verify all unverified claims
Processing:
- Invoke the
cogni-workspace:claimsskill with modeverify - The skill dispatches
claim-verifieragents in parallel (one per unique source URL) - Present verification summary to user
dashboard — Show claims overview
/claims dashboard
/claims dashboard --show-resolved
Display all claims grouped by status with actionable information.
Options:
--show-resolved: include resolved claims in the display
Processing:
- Invoke the
cogni-workspace:claimsskill with modedashboard - Render the formatted dashboard
inspect — Review claim evidence
/claims inspect <claim-id>
Show detailed deviation evidence for a specific claim, with option to open the source in the browser.
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.
- 1mo ago First seen · 196 lines · 0 tokens per session scan A a4066fd0c308
claims is a command published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,339 tokens. 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 2026-09-14.
Other commands, from other repositories
checklist
Use when you need a fast pass over auth, input handling, data, infra, or dependency security in the current code. Do NOT use for deep vulnerability analysis — use /security:audit for that.
speckit.hashloom.seams
Draft hashloom contracts (status: inferred) for the feature's stable seams and register them for gating.
speckit.hashloom.gate
Verify the feature's seams through the hashloom cache: cached-green precheck before implementation, hard verify --radius gate after.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.