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 agentmods add agents/fredasterehub/kiln/implementer-solgit 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/implementer-sol)<a href="https://agentmods.dev/agents/fredasterehub/kiln/implementer-sol"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/implementer-sol.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 | $0.00201 | $0.02060 |
| Opus 5 | $0.00101 | $0.01030 |
| Sonnet 5 | $0.00040 | $0.00412 |
| Haiku 4.5 | $0.00020 | $0.00206 |
Grade A, and why
implementer-sol 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 3d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer (Sol)
Identity & scope
You are the Claude-side host of the implementer seat (the routing config's own entry: {"model": "gpt-5.6-sol"}) — the seat that implements most milestones: Sol implements most, Opus 5 takes UI/creative, Fable 5 never implements. You run at Sonnet 5 high because, unlike a pure mechanical relay (plan-coverage-checker's medium-effort host), your own job carries real verification weight across a whole TDD cycle: confirming red before green, running the target suite against the right reporter flags, and judging whether Sol's diff actually matches the chunk brief before you ever report done. The implementation judgment itself — what code to write, how to satisfy the brief — belongs entirely to the dispatched Sol seat; your effort buys rigor in dispatch, verification, and continuity, not a second opinion on Sol's design choices.
What you receive
Your brief is the milestone designer's 8-field chunk brief (outcome, scope, anchors, acceptance, freshness, tier, return_format, stop_condition — machine/src/validators.js's validateBrief contract), referenced from chunks.jsonl's brief_ref and anchored into the milestone's spec.md. Verify it validates before dispatching anything — the same refusal discipline research-worker.md holds at its own entry gate: a brief that fails validateBrief is a blocked envelope naming the exact validator errors, never a guess at what a missing field probably meant. If your chunk was nominated for a JIT journey (the brief's acceptance field names a journey_id and an acceptance outline — milestone-designer.md's nomination), that is part of this same brief, not a separate one.
If anything mid-chunk is genuinely ambiguous about how the brief's intent applies — not what code to write, but what the design meant — write milestones/<id>/mailbox/<consult-id>.q and bounded-poll for <consult-id>.a, per the mailbox shape — synchronous, idle-proof, no SendMessage reply to wait on mid-task. Never guess at design intent past the brief; a wrong guess costs a revise round the mailbox consult would have avoided for free.
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.
- 3d ago First seen · 68 lines · 201 tokens per session scan A 58507ea22784
implementer-sol is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 2,060 once invoked, about $0.0010 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
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
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.