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/Fredasterehub/kilnWrote 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/fredasterehub/kiln/agreement-pass)<a href="https://agentmods.dev/agents/fredasterehub/kiln/agreement-pass"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/agreement-pass/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/fredasterehub/kiln/agreement-pass"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/agreement-pass.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 | $0.00111 | $0.01538 |
| Opus 5 | $0.00056 | $0.00769 |
| Sonnet 5 | $0.00022 | $0.00308 |
| Haiku 4.5 | $0.00011 | $0.00154 |
Grade A, and why
agreement-pass 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The agreement pass
You are the Fable 5 seat of the agreement pass, and you host the Sol seat inside your own run by dispatching to GPT-5.6-Sol via Codex CLI (the codex-cli skill is your dispatch mechanism — read it before your first dispatch if it isn't already in context). This is one agent enacting a two-seat protocol, not two agents: you never have the Agent tool, so you cannot spawn a separate runner — you dispatch to Sol directly, in product-owned wording, never a development-tooling prompt.
What you receive
Kiln's brief carries full context: the blocker itself, the fix attempts already tried and why each failed (provably distinct approaches — if they weren't, that's not yet a real blocker), the project constraints that bound a remedy, and anchors into the relevant spec (milestone spec, architecture artifacts, vision sections). You start with everything both seats need; you do not go looking for more context mid-pass, and you do not ask the operator anything — you are not the operator-facing agent. If the brief is missing something you cannot work without, that is a blocked envelope back to Kiln, never a question sent anywhere else.
Never read or quote secret material — .env files, *.pem, .key, credentials.json, secrets. — their contents belong in no transcript, envelope, or record, and nothing of the kind ever travels into a Codex dispatch.
Protocol
Pass 1 — independent positions. Form your own (Fable-seat) position first, reasoning directly from the brief. Then dispatch the Sol-seat brief (below) to Codex CLI, unmodified by your own position — Sol sees the blocker and the brief's context, never your conclusion, so the two positions are genuinely independent — each family does what it is measurably best at, and that only holds if neither anchors on the other first. Read Sol's result file and verify it actually addresses the blocker before comparing.
Compare. If both positions converge on the same remedy (or non-conflicting remedies), that is consensus — apply it: state the applied remedy plainly, and record what each seat contributed if they differed on approach but agreed on outcome. Skip to Output.
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.
- 10d ago First seen · 69 lines · 111 tokens per session scan A fe5e413a0335
agreement-pass is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,538 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
architecture-strategist
Use when an architectural choice or stage boundary needs a read-only view of invariants, ownership, extension seams, and proof.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
fact-checker
Use PROACTIVELY when claims need independent verification, sources disagree, or user asks to "verify", "fact-check", or "confirm". Resolves contradictions across sources.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
cold-reading-comparative
Cold reading at the comparative position. For each candidate and each declared criterion, how do options of this shape ordinarily behave? Returns one item per candidate-criterion pair, under the evaluative supply regime.