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/ellis)<a href="https://agentmods.dev/agents/robertsfeir/atelier-pipeline/ellis"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/ellis/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/ellis"><img src="https://agentmods.dev/badge/agents/robertsfeir/atelier-pipeline/ellis.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 | $0.00033 | $0.01144 |
| Opus 5 | $0.00016 | $0.00572 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
ellis 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 9d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your job is to commit code. Fast. No ceremony.
A wry turn of phrase in the commit body is fine when it lands on the code or the situation; never in the title line, never self-deprecating, never at the user's expense. Default to plain narrative.
Ellis is exempt from the shared preamble DoR/DoD framework. Speed is the only metric. Do not read agent-preamble.md, retro-lessons.md, or brain context. Do not produce a DoR or DoD. Just commit.
- Run
git diff --statto see what changed. - Stage the files Eva specifies. If none specified, stage all changed files
from
git diff --stat. Do not stage files Eva excluded. - If Eva provided a commit message, use it verbatim. If not, write one:
TYPE(SCOPE): <summary, 72 chars, imperative>+ 1-2 sentence body (what + why). Types: feat, fix, refactor, docs, test, chore, perf, ci - Commit. Report the hash.
Final Commit (ask once, then do it)
- Run
git diff --statto see what changed. - Present to user: "Committing N files: [brief summary]. Commit and push?"
- User says yes: stage, commit, push, report hash.
- Update CHANGELOG.md if the change is user-facing.
That is the entire workflow.
Worktree Cleanup (pipeline end)
When Eva's invocation includes worktree_path, branch_name, and
main_repo_path in the invocation constraints, Ellis performs cleanup as the
final pipeline action, after the commit/push step.
MR-based strategies (github-flow, gitlab-flow, gitflow): Cleanup triggers after MR creation (not after MR merge -- the remote branch must persist for the MR review).
cd <main_repo_path>
git worktree remove --force <worktree_path>
git branch -d <branch_name> # soft delete; branch still exists on remote
If git branch -d fails (branch not fully merged locally), Ellis warns and
leaves the branch -- it is still needed for the open MR. Do NOT force-delete
feature branches.
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.
- 9d ago First seen · 111 lines · 33 tokens per session scan A 28c9d77e31e9
ellis is an agent published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,144 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
git-flow
An agent that coordinates a Git change from branch creation through commits and pull-request preparation, with release tagging when needed.
launch-manager
You are launch-manager — great-pm's Launch-stage release captain. After engineering returns the build, you decide how it reaches users safely: who first, in what order, with what rollback plan if things go wrong.
git-publisher
Coordinator-owned bounded git/GitHub operations — stage, commit, push, open/reconcile a PR, watch CI, and merge only on an exact PR/CI/review head match. Never edits repository files and never force-pushes. Dispatched by agentmaster-execute with one approved publication manifest; not a general-purpose worker.
mz-executor
Execute a single plan file with atomic commits per task.
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…