loop-triage

A checklist for the first steps of an agentic loop: an operating process where an AI agent repeatedly checks context, acts on work, and records the result. It also covers acknowledging a ticket before later work begins.

In plain words
What is it for?
Use it to check repository documentation and project status, load the right operating profile, review linked Jira or Confluence information, map related repositories, update loop state, and acknowledge Jira tickets.
Why use it?
It reduces missed project context, unclear ownership, and untracked work during issue triage.

Skill for Claude CodeCodexCursor

Install

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.

agentmods
npx agentmods add skills/pallerana/agentic-loop-engineering-kit/loop-triage
Any agent
npx skills add pallerana/agentic-loop-engineering-kit --skill loop-triage
Clone the repo
git clone --depth 1 https://github.com/pallerana/agentic-loop-engineering-kit

Made for: Claude Code, Codex, Cursor.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00051 $0.00431
Opus 5 $0.00026 $0.00216
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 2d ago against content hash c207515a7887, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-triage 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 2d 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.

.cursor/skills/loop-triage/SKILL.md · 46 lines

What it actually says

Loop Triage

Thin wrapper for Phase 0 and Phase 0b of the Agentic Loop Engineering Kit.

Full runbook: .cursor/skills/agentic-loop/SKILL.md via /agentic-loop.

Hard rules

  • Plan mode onlySwitchMode(plan) before any work
  • L1 default — no code or git mutations unless user approves L2+
  • Stop on ambiguity → STATE.md human inbox

Phase 0 checklist

  • python3 scripts/version_check.py
  • Wiki: index.md, current-status.md, log.md
  • Load profile YAML from loop-kit/profiles/<profile>.yaml
  • Profile pattern_doc if set → read (active repo subsection when multi-repo)
  • Profile loop_playbook if set → read
  • Profile context_skill if set (e.g. cell-health-mvp Phase 0)
  • Jira / Confluence per profile
  • graphify query for touched repos
  • Update loop-kit/<profile>-state.md

Phase 0b — Ticket ack

  • Jira: transition to In Progress (Atlassian MCP or jira-cli)
  • Ops: PagerDuty incident note

Log run

.cursor/skills/agentic-loop/scripts/update-loop-state.sh <profile> 0|0b <outcome> <target>

Handoff

After triage, stop for human review (plan-mode-first). Continue with /agentic-loop Phase 1+ only when user approves.

Changes

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.

  1. 2d ago First seen · 46 lines · 51 tokens per session scan A c207515a7887

Subscribe to this mod's changes

loop-triage is a skill published in the GitHub repository pallerana/agentic-loop-engineering-kit (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 431 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

paperclipai/paperclip · 43 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

teammode

Codex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on something as a team in parallel. FIRST inspects the active tool…

code-yeongyu/lazycodex · 238 tokens

omh-agent-board

This is a Hermes-native agent-board workflow skill.

rlaope/oh-my-hermes · 67 tokens

ghostex-cli

Use this skill for anything involving Ghostex or the ghostex/gx CLI: projects and workspaces, terminal panes and sessions, agent orchestration (creating agent sessions, messaging agents, reading their output, queueing prompts, sleeping/waking/killing sessions), scheduled automations, the Kanban/Beads project board…

maddada/Ghostex · 135 tokens

metabot-team

Use for the MetaBot Agent Teams CLI: create and inspect durable Teams, spawn teammates, exchange messages, and manage Tasks and Runs across Sessions.

xvirobotics/metabot · 33 tokens