forge-triage

forge-triage is a skill for Claude Code, Codex from SidCorp-co/forge. It costs 116 tokens per session (2,496 once invoked), scanned A, original, Apache-2.0.

An issue-checking step for Forge, a project management system. It reviews an issue and its history to see whether the request is clear, complete, correctly classified, and ready for planning.

In plain words
What is it for?
Use it to validate issue descriptions, acceptance criteria, category, priority, complexity, and status before development begins.
Why use it?
It catches missing details before developers spend time exploring code or writing an implementation plan. It can use earlier project decisions and issue discussions to interpret the request.

Skill for Claude CodeCodex

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/sidcorp-co/forge/forge-triage
Any agent
npx skills add SidCorp-co/forge --skill forge-triage
Clone the repo
git clone --depth 1 https://github.com/SidCorp-co/forge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for forge-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-triage.svg)](https://agentmods.dev/skills/sidcorp-co/forge/forge-triage)
Your own site
<a href="https://agentmods.dev/skills/sidcorp-co/forge/forge-triage"><img src="https://agentmods.dev/badge/skills/sidcorp-co/forge/forge-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,496 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 $0.00116 $0.02496
Opus 5 $0.00058 $0.01248
Sonnet 5 $0.00023 $0.00499
Haiku 4.5 $0.00012 $0.00250

Measured 4d ago against content hash 416643ea3854, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-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 4d 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.

packages/core/skills/forge-triage/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Triage

Triage gates the pipeline — it catches incomplete issues before they waste expensive planning and coding cycles. An issue that bounces back with questions burns an entire plan-code-review round trip.

Do not read the codebase — triage should be fast and cheap; codebase exploration happens in forge-plan. But you CAN and SHOULD read project memory + issue history: interpreting what an issue is asking for is triage's job, and that context is cheap to pull via MCP tools.

Usage

/forge-triage <documentId>
/forge-triage <documentId1> <documentId2>

Tools

  • forge_issues — get/update issues
  • forge_comments — list/create comments
  • forge_memory_search — recall prior issue outcomes, conventions, decisions before bouncing. You cannot read the codebase, but you CAN read project memory + issue history to interpret an ask.

Workflow

Step 1: Fetch Issue Data

Fetch the issue and its comments in parallel:

forge_issues → get → { documentId: "<id>" }
forge_comments → list → { filters: { issue: "<documentId>" } }

Review all available fields: title, description, acceptanceCriteria, plan, category, priority, complexity, status, comments.

For multiple issues, triage each independently — separate assessments, separate comments.

Step 2: Evaluate Completeness

Read references/triage-criteria.md for the full criteria. The core question: can a developer understand what to change and what the result should be?

DEFAULT = CONFIRM. needs_info is the rare exception, never a safety reflex. For enhancement / improvement / refactor / UI-polish / "make X consistent" issues, the reporter is NOT expected to pre-specify what/where/to-what-pixel — that discovery is the pipeline's job (triage interprets intent → clarify reproduces/captures → plan designs with codebase access). Bouncing such an issue for "missing detail" is itself a triage failure.

Never ask, at triage, for clarify/plan DELIVERABLES: screenshots/visual examples, a per-element diff list, pixel-exact/numeric ACs, which design is the source of truth, an impact/business justification, or specific file/component/endpoint names. If a draft bounce asks for any of these → delete it and CONFIRM with a one-line interpretation note.

Read the full file on GitHub · 201 lines

Files

What ships with it

2 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.

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. 4d ago First seen · 201 lines · 116 tokens per session scan A 416643ea3854

Subscribe to this mod's changes

forge-triage is a skill published in the GitHub repository SidCorp-co/forge (5 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 2,496 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.

Related

Other skills, from other repositories

ai-agent-job-marketplace

The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.

rondoflow/rondoflow · 56 tokens

agent-freelance-bounty-marketplace

Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.

rondoflow/rondoflow · 68 tokens

agent-job-marketplace-with-bidding

Agent-to-agent marketplace MVP. Agents post jobs, bid, contract, submit deliverables, and leave reviews. Payments are off-platform (crypto) in v1.

rondoflow/rondoflow · 41 tokens

advise-engineering-technical-leadership

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO…

rondoflow/rondoflow · 51 tokens

agent-team-collaboration-marketplace

The marketplace for AI agents to form teams and collaborate on projects. Find teammates, join teams, build together.

rondoflow/rondoflow · 30 tokens

agent-marketplace-contracts-trading

Interact with the UID.LIFE agent-to-agent marketplace - register agents, discover workers, send proposals, manage contracts, and transact in $SOUL currency.

rondoflow/rondoflow · 39 tokens