sync-status

A read-only project diagnostic that checks whether active work phases are ready to be closed and finds tracker issues missing from the project plan. A tracker is the system that stores task status.

In plain words
What is it for?
Use it to check phase readiness and find orphaned tracker issues in projects that use Forge plans and a configured task tracker.
Why use it?
It helps reveal when planned tasks are finished and when active issues were created outside the plan. It does not change the phase plan, so the results can be reviewed before taking action.

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/firatcand/forge/sync-status
Any agent
npx skills add firatcand/forge --skill sync-status
Clone the repo
git clone --depth 1 https://github.com/firatcand/forge

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,361 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 $0.00039 $0.01361
Opus 5 $0.00019 $0.00681
Sonnet 5 $0.00008 $0.00272
Haiku 4.5 $0.00004 $0.00136

Measured 3d ago against content hash 3df34f57832a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-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 3d 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/sync-status/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sync-status

Status queries always hit the tracker. plans/phases.yaml is a stale cache. See your project CLAUDE.md §Source of truth.

Read-only diagnostic that answers two questions:

  1. Is any active phase ready for /phase-gate? For each status: active phase in plans/phases.yaml, check whether every task's tracker_issue_id is absent from the tracker's active set. If so, suggest running /phase-gate <phase-id> — never auto-advance.
  2. Are there orphan tracker issues? List tracker issues that are active in the tracker but have no matching tracker_issue_id line anywhere in plans/phases.yaml. These are usually out-of-band hot-fixes the operator may want to backfill.

The skill never writes to phases.yaml. Per-task status drift detection is not possible because phases.yaml has no per-task status field — that's intentional; the tracker is the per-task status authority. See spec/ORCHESTRATOR.md §CLI surface (FORGE-20 readiness algorithm) for the underlying design constraint.

Preflight

  1. Read .forge/settings.yaml. Abort if tracker.type is unset with: "No tracker configured. Run forge init first."
  2. Per-tracker reachability probe (Linear MCP / gh auth status / Notion ntn CLI) — same matrix as /push-to-tracker Step 1. Abort with the setup hint if unavailable. There is no offline fallback.

Steps

  1. Verify plans/phases.yaml exists. If not, abort with: "No plans/phases.yaml found. Run /decompose to generate one."

  2. Fetch active tracker issues — ONE call. Based on tracker.type from settings:

    • Linear: call the Linear MCP list_issues tool with the team filter from settings. Pass no state filter (the adapter excludes terminal states server-side).
    • GitHub: shell out to gh issue list --repo <owner/repo> --state open --json id,number,title,labels,body,url --limit 250.
    • Notion: call the Notion ntn CLI equivalent against the configured data source.

    ONE call total — no per-issue follow-ups. This matches the FORGE-20 design constraint.

Read the full file on GitHub · 92 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.

  1. 3d ago First seen · 92 lines · 39 tokens per session scan A 3df34f57832a

Subscribe to this mod's changes

sync-status is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,361 once invoked, about $0.0002 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 2026-08-30.