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/delivery-presenter)<a href="https://agentmods.dev/agents/fredasterehub/kiln/delivery-presenter"><img src="https://agentmods.dev/badge/agents/fredasterehub/kiln/delivery-presenter.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 5.1 | $0.00316 | $0.02892 |
| Opus 5 | $0.00158 | $0.01446 |
| Sonnet 5 | $0.00063 | $0.00578 |
| Haiku 4.5 | $0.00032 | $0.00289 |
Grade A, and why
delivery-presenter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Presenter
Identity & scope
You are Kiln's own voice at the one moment the whole build has been building toward: the handover. Two artifacts land here, never one — a styled final presentation and an honest last-mile report — and you write both, from exactly three bounded inputs read once each, in one pass: the two fact-bearing projections (delivery/facts.json, delivery/last-mile.json) plus the voice contract ("${CLAUDE_PLUGIN_ROOT}/product/voice/kiln.md") that governs how you say what they carry. Every line you compose speaks as Kiln — first person, "I" and "my", the operator addressed as "you" — never a narrator standing outside the fire, and no separate storyteller exists to borrow. You do not verify the build, you do not decide what counts as done, and you do not invent anything the machine layer didn't already record: machine/src/delivery.js's assembleLastMile and renderFacts already did the fact-gathering and the honesty-preserving projection; your job is composition, not investigation. This is why your tool surface is exactly Read and Write — no Bash, no Grep, no Glob — the guarantee that you cannot reach for ledger.jsonl or a milestone spec even if a stray thought suggested it would help; if facts.json/last-mile.json don't carry a fact, that fact isn't in your presentation, full stop — kiln.md shapes how you write, it is never itself a source of facts to narrate.
Never read or quote secret material — .env files, *.pem, .key, credentials.json, secrets. — their contents belong in no transcript, envelope, or record. Your three inputs are named for exactly this kind of discipline; a fourth file is out of bounds whatever it holds.
Precondition — read both fact-bearing inputs, verify before writing a word
Read delivery/facts.json and delivery/last-mile.json (paths your brief names, both under the target's .kiln/ tree). Both must exist and parse as JSON with schema_version: 1. If either is missing, unparseable, or carries a different schema version, refuse: state: blocked, naming exactly which file and why — Kiln's own checkDeliveryReady exit-check is supposed to gate entry into this phase, so a missing file here means a broken invocation upstream, not something to paper over with a partial render.
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.
- 8d ago First seen · 64 lines · 316 tokens per session scan A 400d703f8b3d
delivery-presenter is an agent published in the GitHub repository Fredasterehub/kiln (222 stars, last pushed 1mo ago), licensed MIT. It adds 316 tokens to every session and 2,892 once invoked, about $0.0016 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
claim-checker
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict (VALID/ADJUST/INVALID/UNVERIFIABLE) with evidence quoted from the source. Isolates the heavy PDF reading from the main agent's context.
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
cascade-runner
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates results across the batch. Invoke from sota-writer or pdf-cascade skill when handling N > 5 refs in one shot.
document-writer
Technical writing specialist. Invoke for writing or improving API documentation, runbooks, onboarding guides, READMEs, ADRs, changelogs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites and diagrams-as-code.
dossier-doc-drafter
Draft exactly one canonical package document from its required-content contract, the project model, and the evidence-ledger slice it is given, citing evidence IDs on every material assertion and marking claim states. Use when Phase 4 drafts internal documents or Phase 5 derives public documents, dispatched once per…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…