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 skills/affectionatec/agentic-engineering/run-loopnpx skills add affectionatec/agentic-engineering --skill run-loopgit clone --depth 1 https://github.com/affectionatec/agentic-engineeringWhat 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 | $0.00119 | $0.00909 |
| Opus 5 | $0.00060 | $0.00454 |
| Sonnet 5 | $0.00024 | $0.00182 |
| Haiku 4.5 | $0.00012 | $0.00091 |
Grade A, and why
run-loop 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Loop
Drive the documentation chain end-to-end without per-task prompting. You are the producer; verification is dispatched to a fresh-context verifier, never self-graded; merging is never yours.
Target
Parse the user's instruction:
- A milestone (e.g.
M2) → run its tasks in dependency order until the milestone is done - A task ID (e.g.
M2-T3) → run exactly that task until-blocked→ keep taking the next unblocked task until nothing is runnablemax-tasks=N→ cap on tasks this run (default 5; the user must raise it explicitly for longer runs)
No target given → ask for one before looping. Do not guess.
Preconditions — abort with a clear message if unmet
AGENTS.md,docs/plans/implementation-plan.md, anddocs/status.mdexist. If not, stop and route to theusing-agentic-engineeringrouter — a loop without the chain is just unsupervised guessing.- Working tree is clean and
mainis up to date. - The In-Flight Checkpoint in
docs/status.mdisnone. If it isn't, the previous session crashed — run the status-tracker recovery protocol first, then loop.
Loop body — per task
- Pick the next unblocked task for the target (STATUS module table + plan dependency order).
- Branch per the git-workflow skill:
task/<task-id>-<slug>from up-to-date main. - Build to the spec. Producer self-check: lint clean, full suite passing, test ratchet holds.
- Checkpoint
docs/status.md: In-Flight Checkpoint updated, module table → 🔍. - Ship: push the branch, open a draft PR whose description carries the task reference and done condition (git-workflow PR protocol).
- Verify: dispatch a fresh-context verifier with the task ID, branch name, and done-condition location — the bundled
verifiersub-agent where the harness supports it, otherwise any fresh-context mechanism per the independent-verification skill (a fresh session or separate agent). Never verify your own work in this conversation. - On PASS: STATUS module table → ✅ with verdict + PR references; flip the PR from draft to ready; proceed to the next task.
- On FAIL: fix on the same branch (each round noted in the PR), re-dispatch the verifier. Three consecutive FAILs on one task stops the entire loop — escalate to the user with the verdict history.
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 · 57 lines · 119 tokens per session scan A 21d56df5235a
run-loop is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 909 once invoked, about $0.0006 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 skills, from other repositories
vibe-to-agentic-framework
The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
presentation-structure
Knowledge about the presentation slide format, weight system, navigation, and section structure.
presentation-styling
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation.
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.
time-skill
Display the current time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.