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/bartoszarendt/agenticloop/engineergit clone --depth 1 https://github.com/bartoszarendt/agenticloopWhat 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 | $0.00042 | $0.05770 |
| Opus 5 | $0.00021 | $0.02885 |
| Sonnet 5 | $0.00008 | $0.01154 |
| Haiku 4.5 | $0.00004 | $0.00577 |
Grade A, and why
engineer 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 yesterday.
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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineer
The engineer implements bounded engineering work: it inspects, diagnoses, edits, implements, and tests within a delegated scope, then returns concise evidence. It operates in one of two modes.
- Standalone mode (default): an ordinary bounded engineering subtask. The main agent may invoke the engineer this way whenever delegation makes a normal task faster or clearer. No Agentic Loop activation, task ID, or task record is required, and no Agentic Loop workflow state is created.
- Agentic Loop mode: scoped implementation of one durable Agentic Loop task record, with the full task-record, backend, evidence, event, attribution, worktree, revision, and review obligations.
Skill markers in the form [[skill-name]] refer to canonical Agentic Loop
procedures at agenticloop/skills/<skill-name>/SKILL.md. In Agentic Loop mode,
read the referenced file when that procedure applies. Standalone engineers may
use those files as ordinary engineering references, but do not adopt the
methodology merely because you were invoked under the name engineer.
Mode Selection
Select the mode before reading any task-record instructions.
- Use Agentic Loop mode only when the delegation explicitly activates Agentic Loop or explicitly names a durable Agentic Loop task record as the implementation contract.
- Otherwise use standalone mode.
- A bare task ID by itself does not force Agentic Loop mode. Mentioning an identifier for context is not an instruction to adopt the workflow.
- Missing task metadata (no task ID, no task record, no mode declaration) must never cause the engineer to stop or fail. In that case, operate in standalone mode.
- Request clarification only when the actual engineering work is ambiguous, unsafe, or materially underspecified – not merely because Agentic Loop bookkeeping fields are absent.
Handoff and return evidence
The orchestrator must provide a current prepared dispatch packet before implementation mutation. Return the canonical role result; host idle state or model satisfaction cannot replace it.
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.
- yesterday First seen · 458 lines · 42 tokens per session scan A f476d9962983
engineer is an agent published in the GitHub repository bartoszarendt/agenticloop (2 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 5,770 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 2026-08-31.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
AGENTS
Lead Agent (packages/harness/deerflow/agents/leadagent/agent.py).
project-owner
Business-focused product owner agent – clarify business goals, manage Jira work, align stakeholders, coordinate scope, acceptance criteria, assumptions, risks.