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/jmagly/aiwgnpx agentmods add skills/jmagly/aiwg/agent-loopWrote 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/jmagly/aiwg/agent-loop)<a href="https://agentmods.dev/skills/jmagly/aiwg/agent-loop"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/agent-loop/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/jmagly/aiwg/agent-loop"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/agent-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 94 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 141 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium MCP Rug Pull · line 159 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 221 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00017 | $0.04604 |
| Opus 5.5 | $0.00007 | $0.01842 |
| Sonnet 5.5 | $0.00003 | $0.00921 |
| Haiku 4.5 | $0.00002 | $0.00460 |
Grade A, and why
agent-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 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill access pattern (post-kernel-pivot, 2026.5+)
Skill names referenced in this document are AIWG skills, not slash commands. Most are not kernel-listed and cannot be invoked as
/skill-nameby the platform. Reach them via:aiwg discover "<capability>" aiwg show skill <name>Only kernel-listed skills (
aiwg-doctor,aiwg-refresh,aiwg-status,aiwg-help,use,steward) are directly invokable as slash commands. See skill-discovery rule.
Agent Loop Skill
You detect when users want iterative autonomous task execution and route to an internal, in-session loop by default. External daemon loops are opt-in and require an explicit request.
Loop Taxonomy
This skill is the detection and routing layer for autonomous agent loops — iterative patterns where a single agent retries a task against completion criteria until success or limits.
| Loop Type | Implementation | Description |
|---|---|---|
| Internal Agent Loop | current assistant session / internal loop | Default visible iterate-until-complete workflow in the active session |
| Al | internal ralph concept |
Basic iterate-until-complete when named without external qualifiers |
| External Agent Loop | agent-loop-ext / ralph-external daemon |
Explicitly requested background, detached, crash-resilient, or resumable work |
| (future) | — | Reflection loops, critic-actor loops, branching loops |
Generic loop requests route to the internal in-session loop. As new loop types are added, this skill will route based on task characteristics.
Routing Policy
Step 0: Provider Capability Check
Before choosing the loop mechanism, detect the active provider via aiwg runtime-info or the steward capability surface. The provider branch is internal to this skill; users invoke the same agent-loop / ralph names everywhere.
| Provider capability | Route | Notes |
|---|---|---|
Provider with native /goal (Codex, Claude Code) |
Delegate the in-session loop to /goal |
Convert the task plus completion criterion into a standing goal. If a programmatic goal tool is unavailable, print the exact /goal "..." command for the operator instead of emulating a duplicate loop. |
| Provider with native dynamic orchestration (Claude Code Workflow tool) | In-session multi-agent fan-out MAY delegate to the native orchestration tool | AIWG retains audit, gates, best-output selection, and cross-session durability. The native tool is in-session/background scoped — NOT a detached daemon — so detached/resume-after-session work stays AIWG-native (see external row). |
| Other providers | AIWG internal loop discipline | Keep the existing visible act/verify/adapt cycle in the current session. |
| Explicit external/background request | agent-loop-ext / ralph-external |
Detached, crash-resilient, resume-after-session-ends work stays AIWG-native: /goal is in-session, and the Claude Code Workflow tool is session-scoped. Codex has no core /workflow (verified, codex-cli 0.135.0, #1535). |
What ships with it
1 file 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.
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 · 428 lines · 17 tokens per session scan A 88f527860ecc
agent-loop is a skill published in the GitHub repository jmagly/aiwg (224 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 4,604 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
builder
Implementing robust business logic, API integrations, data models, and reproducible AI image-generation code with type safety. Use for production implementation, Gemini image API pipelines, or interactive pair programming.
matrix
Controlling combinatorial explosion across multi-dimensional axes: minimum coverage sets, execution plans, test/deploy/UX/risk prioritization. Use when scoping multi-axis combinations.
nexus
Orchestrating multi-specialist task chains and scope-adaptive product delivery: classifies intent, selects and executes the minimum viable chain, aggregates results, and verifies acceptance criteria. For multi-domain tasks, build-first delivery, and product lifecycle execution.
oracle
Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.
scribe
Authoring standalone and cross-team specifications: PRD/SRS/HLD/LLD, staged L0-L4 unified packages, BDD acceptance criteria, and traceability. Use for technical or multi-audience documentation; not implementation or architecture decisions.
tome
Converting technical knowledge into durable learning documents and publishable articles. Use for diff-based teaching, decision records, onboarding, note/Zenn/Qiita/dev.to posts, article series, retrospectives, and cross-platform repurposing.