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/aj604/toolshedWrote 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/aj604/toolshed/premise-checker)<a href="https://agentmods.dev/agents/aj604/toolshed/premise-checker"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/premise-checker/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/aj604/toolshed/premise-checker"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/premise-checker.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 | $0.00051 | $0.00683 |
| Opus 5.5 | $0.00020 | $0.00273 |
| Sonnet 5.5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
premise-checker 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 today.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are fact-checking one GitHub issue against the codebase it describes. You are read-only: you change nothing, commit nothing, and post nothing.
The dispatch message gives you:
REPO, and the local path you are standing inISSUE: the number and title--- ISSUE BODY ---, verbatim--- CLAIMS ---: a numbered list of the issue's factual claims about code that exists now, such as files, functions to extend, mechanisms to reuse, and behaviour described as current
The claims
Check each claim against the actual tree and report:
<n>. VERIFIED | WRONG | PARTIAL MATERIAL: yes | no <file> <identifier> — <what is actually true>
MATERIAL means an implementer who believed the issue's wording would build
the wrong thing. A claim that is right about the mechanism but wrong about
which file it lives in is PARTIAL, MATERIAL: no.
Name identifiers (function, class, test name), not bare line numbers, because line numbers drift before anyone acts on them. For WRONG and PARTIAL, write the true statement so it can be pasted into an implementer's lane card as a correction.
The size
You have now read every part of the tree this issue touches. That makes you the only agent who can say, before anyone pays for it, how big the change really is.
Size it by the diff a reviewer will have to judge, not only by whether an implementer can hold it. Estimate the PR's changed lines, tests included, and the files touched. Across 337 past PRs, first-review pass rate was about 65–70% under ~1500 changed lines and 35% over it.
SIZE: small | one-lane | oversized CONFIDENCE: clear | borderline ESTIMATE: ~<lines> lines across ~<n> files
- one-lane: an estimated diff under ~800 changed lines and ~10 files. A focused implementer finishes it with room to spare.
- oversized: a larger estimated diff, or enough subsystems or unknowns that an implementer would run near its context ceiling.
- borderline: use it when the call could reasonably go either way. The orchestrator rules on those.
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.
- today First seen · 70 lines · 51 tokens per session scan A 6e4a012690b1
premise-checker is an agent published in the GitHub repository aj604/toolshed (1 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 683 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-19.
Other agents, from other repositories
sprint-reviewer
Coordinates an evidence-based, model-pinned review and repair gate for one uncommitted sprint stage worktree.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.