Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitnpx agentmods add skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineeringWrote 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/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineering)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineering"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineering/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/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineering"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/loop-engineering.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 | $0.00060 | $0.01070 |
| Opus 5.5 | $0.00024 | $0.00428 |
| Sonnet 5.5 | $0.00012 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
loop-engineering 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loop Engineering
Operational skill distilled from 125-source full ingest (93 non-GitHub line-indexed + 33 GitHub code audits). Load REFERENCE.md for doctrine; INSTALL.md for code-backed installs; CORPUS_INDEX.md for source digests.
v2 requirement — evidence before recommendation
Before recommending any repo or install path:
- Run
python3 scripts/load-digest.py --repo {slug}OR readdata/repo-audits/{owner__repo}.md - Cite evidence IDs (E###) or audit locators (
file:line) in your answer - Flag README-vs-code mismatches when audit notes them
Do not recommend installs from REFERENCE.md alone.
When to use
- User asks to design a loop, harness, or agent workflow
- Choosing between
/loop,/goal, Routines, Ralph, or custom bash engines - Picking an installable repo vs custom skill/agent
- Wiring verification, state write-back, or human-in-the-loop gates
Decision tree
Need recurring agent work?
├─ Yes → Stop condition verifiable?
│ ├─ Yes → Maturity path (below)
│ └─ No → Fix stop condition first; do not schedule
└─ No → Single-shot skill dispatch; not a loop
Maturity path (jpoindexter / corpus consensus):
1. Reliable manual run (one skill, one outcome)
2. Encode as SKILL.md
3. Add state file or kernel write-back
4. Wrap in gated loop (mechanical + human gate)
5. Schedule via /loop or /goal
Loop contract template
Every loop design MUST specify:
| Field | Question |
|---|---|
| Trigger | Schedule, event, or human /loop |
| Input state | What the agent reads (files, DB, kernel) |
| Skill/playbook | Which SKILL.md stages run |
| Verifier | Separate checker sub-agent or mechanical gate |
| Stop condition | Boolean test — not vibes |
| Write-back | What persists after each cycle |
| Human gate | When human must approve before next cycle |
Harness primitives (use first)
| Primitive | Use when |
|---|---|
/loop |
Fixed interval re-run of prompt or slash-command |
/goal |
Run until separate model grades "done" |
| Routines | Anthropic-documented recurring workflows |
| Sub-agents | Maker builds; checker verifies (never same agent) |
| Context kernel | Cross-session state at .kernel/KERNEL.md |
What ships with it
40 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CORPUS_INDEX.md 28 KB
- data/corpus-index.json 28 KB
- data/repo-audits/agentic-in__inferoa.md 4.1 KB
- data/repo-audits/alchaincyf__harness-engineering-orange-book.md 1.3 KB
- data/repo-audits/alchaincyf__loop-engineering-orange-book.md 2.8 KB
- data/repo-audits/AlexDuchDev__AgenticMind.md 3.8 KB
- data/repo-audits/bhavinkotak__agentforge.md 2.9 KB
- data/repo-audits/blazov__living-board.md 5.0 KB
- data/repo-audits/ChaoYue0307__awesome-loop-engineering.md 5.1 KB
- data/repo-audits/cobusgreyling__loop-engineering.md 4.8 KB
- data/repo-audits/colbymchenry__codegraph.md 4.0 KB
- data/repo-audits/DreamChaserEric__claude-lights-out.md 2.8 KB
- data/repo-audits/Dryxio__auto-re-agent.md 3.0 KB
- data/repo-audits/earendil-works__pi.md 5.3 KB
- data/repo-audits/emosamastudio__agent-hub.md 3.6 KB
- data/repo-audits/Forward-Future__loop-library.md 3.6 KB
- data/repo-audits/Fractera__Agent-Engineering-Infrastructure.md 4.7 KB
- data/repo-audits/FUY25__Loop.md 4.2 KB
- data/repo-audits/jpoindexter__ai-agent-skills.md 3.8 KB
- data/repo-audits/juliusbrussee__caveman.md 3.5 KB
- data/repo-audits/microsoft__SkillOpt.md 4.1 KB
- data/repo-audits/mikulgohil__se-agent-platform.md 2.7 KB
- data/repo-audits/ordinary9843__gitizens.md 2.6 KB
- data/repo-audits/pgmnemo__pgmnemo.md 2.5 KB
- data/repo-audits/rlaope__oh-my-hermes.md 4.7 KB
- data/repo-audits/rtk-ai__rtk.md 3.1 KB
- data/repo-audits/sneg55__agent-starter.md 2.6 KB
- data/repo-audits/Stahl-G__briefloop.md 5.3 KB
- data/repo-audits/thu-nmrc__openloop.md 2.6 KB
- data/repo-audits/valkor-ai__loom.md 5.8 KB
- data/repo-audits/vinnylarouge__skill-opt-skill.md 5.1 KB
- data/repo-audits/WAPA0012__cc-loop-engineering.md 2.7 KB
- data/repo-audits/Windy3f3f3f3f__how-claude-code-works.md 4.6 KB
- data/repo-audits/wquguru__harness-books.md 5.0 KB
- data/repo-audits/xpriment626__pi-factory.md 2.2 KB
- data/repo-scorecard.json 32 KB
- INSTALL.md 931 B
- REFERENCE.md 3.4 KB
- scripts/load-digest.py 2.4 KB runs code
- scripts/repo-pick.py 3.1 KB runs code
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.
- 1mo ago First seen · 112 lines · 60 tokens per session scan A 4b854af01e81
loop-engineering is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 21d ago), licensed MIT. It adds 60 tokens to every session and 1,070 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
sharp-edges
Identify error-prone APIs, dangerous configuration, and footgun designs that enable security mistakes. Use for API ergonomics, misuse resistance, secure defaults, or pit-of-success reviews; use code-review for general defects.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
code-reviewer
Review code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter. Use this skill when reviewing a small set of changes locally (such as unstaged diff), when dispatched as a…
differential-review
Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.