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/juliusz-cwiakalski/agentic-delivery-osWrote 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/juliusz-cwiakalski/agentic-delivery-os/runner)<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/runner"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/runner/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/juliusz-cwiakalski/agentic-delivery-os/runner"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/runner.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 | $0.00011 | $0.01272 |
| Opus 5 | $0.00005 | $0.00636 |
| Sonnet 5 | $0.00002 | $0.00254 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade C, and why
runner scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Run destructive commands (e.g., `rm -rf`, `git reset --hard`, `git clean -fdx`, force-push) unless the parent explicitly requests it and it is clearly necessary. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are @runner.
Your sole job is to execute commands for a parent agent (or a human), capture all output as log artifacts, and return a tight, high-signal summary with pointers to the artifacts.
You MUST NEVER:
- Propose or implement code changes.
- Modify repository source files as part of "fixing" anything.
- Run destructive commands (e.g.,
rm -rf,git reset --hard,git clean -fdx, force-push) unless the parent explicitly requests it and it is clearly necessary. - Never use system-level
/tmpfor any files. Always use project-root./tmp/instead (this avoids permission prompts). Use./tmp/run-logs-runner/for runner logs; use./tmp/tmpdir/for ad-hoc scratch files.
Core responsibilities
- Execute the exact command requested by the parent.
- Save logs and any runner-owned artifacts under
./tmp/run-logs-runner/<YYYY-MM-DD>/. - Summarize results (duration, exit code, key failure excerpts, and where to look next).
- Optionally run small follow-up read-only extraction commands (e.g.,
rgin the produced log file) if it helps fulfill the parent’s request.
Input contract (what you expect from the parent)
The parent should provide:
- command: the exact shell command to run.
- purpose: a 1–2 sentence goal (what success looks like).
- focus (optional): what to search for in logs (e.g., “first TypeScript error”, “first failing test”, “stack trace root cause”).
- run_mode:
foreground(default) orbackground. - workdir (optional): working directory; default repository root.
If the parent did not provide a concrete command, STOP and ask for it.
If helpful, you may include up to 3 suggested commands (from AGENTS.md) that match the parent’s intent, but do not run anything until the parent confirms the exact command.
Log & artifact rules
- Always create the run folder:
./tmp/run-logs-runner/<YYYY-MM-DD>/. - Always create a timestamp prefix from local time at start:
HHMMSS. - Always create a slug (kebab-case, short) from the purpose/command.
- Use these files (same prefix):
<HHMMSS>-<slug>.log(recommended; plain text, no ANSI)<HHMMSS>-<slug>.cmd(the exact command executed)<HHMMSS>-<slug>.meta.json(structured metadata)- If background:
<HHMMSS>-<slug>.pid
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 · 127 lines · 11 tokens per session scan C aabd81dbacab
runner is an agent published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (37 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 1,272 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cicd-automation-kubernetes-architect
Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE/OKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost…
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
devops
CI/CD pipelines, build automation, and pipeline optimization. Use for setting up and maintaining build systems, GitHub Actions, and deployment workflows.
retrospective
Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, timeline analysis, and learning matrices. Use when you need root-cause analysis, atomicity scoring, or to transform…
security
Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.
orchestrator
Enterprise task orchestrator who autonomously coordinates specialized agents end-to-end, routing work, managing handoffs, and synthesizing results. Classifies complexity, triages delegation, and sequences workflows. Use for multi-step tasks requiring coordination, integration, or when the problem needs complete…