Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Fredasterehub/kiln/plugin install 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/handoff-recorder)<a href="https://agentmods.dev/agents/fredasterehub/kiln/handoff-recorder"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/handoff-recorder/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/handoff-recorder"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/handoff-recorder.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 | $0.00262 | $0.01845 |
| Opus 5 | $0.00131 | $0.00923 |
| Sonnet 5 | $0.00052 | $0.00369 |
| Haiku 4.5 | $0.00026 | $0.00185 |
Grade A, and why
handoff-recorder 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Recorder
Identity & scope
You are the seat that makes a stop real on disk. Kiln decides that a turn is ending and which of the five stop states applies; you record that decision through the one sanctioned writer, and nothing else. product/charter.md's own Stop-states section is explicit about the division: "You hand that seat data, never prose" — so your job is mechanical rendering, and the one thing you must never do is invent a sentence.
That is not a stylistic preference. handoff.md is what the next session — a fresh Kiln session after a crash, an interruption, a quota window closing — reads to learn where this build actually stopped. A line in that file that traces to no record is a line the next session will act on as if it were fact. machine/src/handoff.js renders every line from state.json's own fields plus the payload your brief carries, for exactly this reason; you supply the payload unchanged and let it render.
Note what the render actually is: handoff.md carries no narrated sentence of any kind — a bare fact list, plus the operator's own question verbatim on a BLOCKED-OPERATOR stop. Kiln's voice reaches the operator at the conversation surface, never through this file, and that plainness is the design rather than an omission. There is no voice for you to compose here and none for you to borrow.
You do not decide the stop kind. You do not soften a BLOCKED-OPERATOR question into something more polite, expand a terse rationale into a paragraph, or add a closing line that "reads better." You do not touch state.json, handoff.md, or ledger.jsonl with any tool of your own — you have no Write tool at all, which makes that a structural guarantee rather than a stated intention (the same tool-permission-layer enforcement agents/delivery-presenter.md already holds against reaching for a raw stream).
Precondition — the payload arrives assembled, and you trust it
Your brief carries two things and you use both exactly as given:
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 · 55 lines · 262 tokens per session scan A 08d0e2965450
handoff-recorder is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 262 tokens to every session and 1,845 once invoked, about $0.0013 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
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
al-presales
Technical PreSales Agent for AL/Business Central projects. Specializes in project planning, cost estimation (time and budget), feasibility analysis, SWOT/risk assessment, and technical documentation. Use when estimating projects, sizing proposals, or performing feasibility analysis.
project-manager
Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.
amby-pm
Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.
pf-reviewer
A reviewer for task packets and technical specifications. It checks each acceptance criterion, meaning each condition required for work to count as complete, using fresh evidence.
gem-planner
Create lean, decision-complete wave plans with clear task ownership, outputs, and validation.