agentmods.dev

Forge: Skill for Claude Code

.claude/skills/forge-status/SKILL.md

forge-status is a skill for Claude Code from lionshilov/Forge. It costs 30 tokens per session (343 once invoked), scanned A, original, MIT.

A project-status report for a Forge codebase that checks phase gates, tasks, recent failures, blockers, Git changes, and the next recommended action.

In plain words
What is it for?
It is for checking project gates, reviewing completed and blocked work, finding repeated errors, and choosing the next step.
Why use it?
It exposes mismatches between the task board and the actual files or commits, so progress reports are based on the repository.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lionshilov/Forge's own configuration. It tells Claude Code how to work on Forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Forge configures →

not rated 5repo 1mo ago A scan 30 tokens original MIT
View source ↗ lionshilov/Forge
Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lionshilov/Forge/main/.claude/skills/forge-status/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lionshilov/Forge

Made for: Claude Code.

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-status

README.md
[![agentmods](https://agentmods.dev/badge/skills/lionshilov/forge/forge-status/github.svg)](https://agentmods.dev/skills/lionshilov/forge/forge-status)
Your own site
<a href="https://agentmods.dev/skills/lionshilov/forge/forge-status"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-status/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.

agentmods 80×15 button for forge-status

Your own site · 80×15
<a href="https://agentmods.dev/skills/lionshilov/forge/forge-status"><img src="https://agentmods.dev/badge/skills/lionshilov/forge/forge-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.00343
Opus 5.5 $0.00012 $0.00137
Sonnet 5.5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured today against content hash 4a965606fd02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forge-status 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 today.

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.

.claude/skills/forge-status/SKILL.md · 21 lines

What it actually says

You are the Forge Orchestrator. Produce a status report:

  1. Run bash .claude/hooks/forge-gate.sh status — the phase-gate board (which context files are template / draft / ready, and which agents each closed gate blocks), open tasks, latest errors.
  2. Read project_context/PROGRESS.md and project_context/ERRORS_LOG.md (last 5 entries max) where the board isn't enough.
  3. Run git log --oneline -10 and git status --short for ground truth on what actually changed.
  4. Cross-check: tasks marked 🟢 Done should have corresponding commits/files, and a context file marked ready should hold real decisions, not template placeholders. Flag mismatches — a board that lies is worse than no board.

Report back:

  • Gates — which are closed and what each one blocks
  • Done / In progress / Blocked — one line per task, straight from the table
  • Failures worth attention — repeated ERR- entries or tasks approaching the 3-retry escalation limit
  • Next action — the single highest-leverage next step per the Routing Rules in root CLAUDE.md; usually opening the closed gate that blocks queued work (e.g. "DESIGN.md is template but a UI task is queued → dispatch Designer first")

Do not start executing the next action — report and wait for the user.

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. today First seen · 21 lines · 30 tokens per session scan A 4a965606fd02

Subscribe to this mod's changes

forge-status is a skill published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 343 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 2026-11-07.

Git and workflowLLMMulti-AgentProject managementai-agentsanthropicclaude
Related

forge-status compared with skills from other repositories

forge-status next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
forge-statuslionshilov/ForgeSkill51mo agoMITA30Claude Code
github-repo-managementgraniet/kheishSkill213todayApache-2.0A42Claude Code, Codex
github-code-reviewgraniet/kheishSkill213todayApache-2.0A41Claude Code, Codex
github-authgraniet/kheishSkill213todayApache-2.0A45Claude Code, Codex
github-pr-workflowgraniet/kheishSkill213todayApache-2.0B44Claude Code, Codex
deployment-patternsaffaan-m/ECCSkill299ktodayMITA41Claude Code, Kiro
publish-siteNousResearch/hermes-agentSkill261ktodayMITA19Claude Code, Codex