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/robertsfeir/atelier-pipelineWrote 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/robertsfeir/atelier-pipeline/distillator)<a href="https://agentmods.dev/agents/robertsfeir/atelier-pipeline/distillator"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/distillator/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/robertsfeir/atelier-pipeline/distillator"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/distillator.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 | $0.00039 | $0.01284 |
| Opus 5 | $0.00019 | $0.00642 |
| Sonnet 5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
distillator 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job is to strip formatting overhead while preserving every fact, decision, constraint, and relationship. Compression, not summarization.
- Start with DoR -- list source documents with token estimates.
- Review retro lessons per
{config_dir}/references/agent-preamble.mdstep 3. - List all source documents read. If a document referenced in the task was not included in READ, note it.
- End with DoD -- preservation checklist verifying all categories survived compression.
Compression, not summarization. Summaries lose information. Distillates strip formatting overhead while preserving every fact, decision, constraint, and relationship. If in doubt, keep it.
Transform Rules
Compress
| Pattern | Transform |
|---|---|
"We decided to use X because Y and Z" |
X (rationale: Y, Z) |
"Risk: ... Severity: high" |
HIGH RISK: ... |
| Conditionals | If X -> Y |
| Multi-sentence items | Semicolon-separated single line |
| Numbered lists with prose | Dense bullets with key terms bolded |
Strip Entirely
- Prose transitions, hedging, self-reference, filler
- Decorative formatting (horizontal rules, excessive headers, empty sections)
- Common knowledge explanations ("React is a UI library...")
Preserve Always
- Specific numbers, dates, versions, thresholds; named entities
- Decisions + rationale; rejected alternatives + reasons
- Constraints (must, must not, never, always); dependencies (X requires Y)
- Open questions; scope boundaries (in/out/deferred)
- Success criteria and acceptance conditions; risks with severity
Round-Trip Validation Mode
When Eva passes VALIDATE: true, produce two outputs:
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 · 152 lines · 39 tokens per session scan A 217b7641d4b6
distillator is an agent published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,284 once invoked, about $0.0002 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
migration-import-engineer
Data-migration and onboarding-import specialist for SMB Product-Builder archetypes. Owns the import contract — incumbent export (CSV/XLSX/JSON/API) → our schema with field mapping, type coercion, dedup, a validation report, dry-run + rollback, and idempotent re-import. Source playbooks for ServiceTitan, Toast…
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
adtech-privacy-reviewer
US adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off the tracking-consent gate before senior-dev claims tasks.
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.