A checker for determining whether project planning files in a `.forge` folder are still current after related requirements or architecture change. It reports outdated files and the order in which they should be updated.

Use it before building, reviewing, or shipping when upstream project files have changed, or when you need to know what must be regenerated.

It helps prevent later work from relying on documents that no longer match the project's decisions.

forge-sync — Skill for Claude Code by aneja5/forge-skills

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.

Any agent

npx skills add aneja5/forge-skills --skill forge-sync

Clone the repo

git clone --depth 1 https://github.com/aneja5/forge-skills

Made for: Claude Code.

Or install forge-skills, the plugin that ships this one along with the rest of its 42 skills, 36 commands, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aneja5/forge-skills/forge-sync/github.svg)](https://agentmods.dev/skills/aneja5/forge-skills/forge-sync)

Your own site

<a href="https://agentmods.dev/skills/aneja5/forge-skills/forge-sync"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/forge-sync/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aneja5/forge-skills/forge-sync"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/forge-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,393 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.04393
Opus 5.5	$0.00026	$0.01757
Sonnet 5.5	$0.00013	$0.00879
Haiku 4.5	$0.00007	$0.00439

Measured 1mo ago against content hash d323093a20e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forge-sync 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.

skills/forge-sync/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

forge-sync

Overview

Scan every .forge/ artifact for  headers, cross-reference against references/forge-dependency-graph.md, and produce .forge/sync-report.md listing stale artifacts and the topologically-sorted cascade to re-sync. Pairs with every artifact-producing skill — forge-sync does not regenerate anything; it tells you what to re-run.

When to Use

A change landed in an upstream artifact (PRD edited, architecture updated, contracts revised) and downstream artifacts may be stale
Before /build, /review, or /ship — confirm the chain is consistent
After a teammate's PR touches .forge/ — verify your local view is in sync
User asks "is anything out of date" / "what needs to be regenerated" / "is the chain consistent"

When NOT to Use

No .forge/ directory exists yet — nothing to sync
Single greenfield session where no artifacts have been produced
The user just wants to read an artifact, not check its freshness

Common Rationalizations

Rationalization	Rebuttal
"The change was small, downstream is probably fine"	Small PRD changes cascade into contract mismatches that surface as bugs during build.
"I'll sync later before shipping"	Stale contracts mean `/review` validates against outdated interfaces. The mismatch is invisible until production.
"Only the architecture changed, tasks are still valid"	Architecture changes invalidate task file-lists and dependency ordering.
"I just want to update one artifact"	Partial syncs leave the chain inconsistent. Run the full cascade.
"I'll trust the timestamps in memory"	Memory lies. Read the headers; they're the source of truth.

Red Flags

architecture.md references modules not in .forge/contracts/
tasks.yaml references contracts that don't exist on disk
PRD describes features not in architecture
generated_at timestamps show downstream older than upstream
generated_at strings are not UTC (no Z suffix, or contain +/- offset)
An artifact's on-disk content sha256 doesn't match its stored content_hash (hand-edited after generation)
Multiple .forge/ artifacts with no forge:meta headers (untracked → run /forge-migrate)
User running /build without checking sync first

Read the full file on GitHub · 276 lines

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.

1mo ago First seen · 276 lines · 66 tokens per session scan A d323093a20e5

Subscribe to this mod's changes

forge-sync is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 4,393 once invoked, about $0.0003 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 2026-09-03.

Claude Code Planning Project management agentic-engineering agents claude-code-plugin claude-code-skills design-system

link-ticket-to-session

Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…

JayantDevkar/claude-code-karma · 91 tokens

forge-sync

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

forge-sync

Overview

When to Use

When NOT to Use

Common Rationalizations

Red Flags

What this file has done since we first saw it

Other skills, from other repositories

link-ticket-to-session

lead

to-tickets

swarm-swarm

build-flow

add-azuredevops