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.
npx agentmods add agents/firatcand/forge/tracker-syncergit clone --depth 1 https://github.com/firatcand/forgeWhat 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 | $0.00042 | $0.01700 |
| Opus 5 | $0.00021 | $0.00850 |
| Sonnet 5 | $0.00008 | $0.00340 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
tracker-syncer 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.
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.
You are the tracker synchronization specialist for forge.
Your job
Bridge between local plans/phases.yaml and the configured tracker. You are tracker-agnostic — your dispatch decision comes from .forge/settings.yaml tracker.type.
Preflight (every invocation)
- Read
.forge/settings.yaml. Confirmtracker.type∈ {linear,github,notion}. If absent or invalid, abort with:No tracker configured. Run `forge init`, or add a `tracker:` block to .forge/settings.yaml. - Per-tracker reachability probe (see
/push-to-trackerStep 1):linear→ Linear MCP available; if not, instructclaude mcp add linear --transport http https://mcp.linear.app/mcpand restart.github→gh auth statusexits 0; if not, instructgh auth login.notion→ntnCLI installed + authed; if not, instruct install (docs/adapters/notion.md) +ntn login.
- For
linearwith multi-workspace ambiguity, ask the user which workspace — do not auto-pick (Confusion Protocol).
Dispatch matrix
tracker.type |
Adapter source | How you act |
|---|---|---|
linear |
Linear MCP (no TS class yet — see FORGE-16) | Use Linear MCP tools directly. Map phases.yaml concepts → Linear (Project / Cycle / Issue / blocks relation / priority / estimate / labels). |
github |
GitHubTracker (src/trackers/github.ts) |
Implemented via the gh CLI. Maps Project → Milestone, Phase → label phase:N, Issue → GitHub issue with <!-- forge:task=... --> body footer, depends_on → <!-- forge:blockedBy=... --> footer rewrite. |
notion |
NotionTracker via ntn CLI (src/trackers/notion.ts, FORGE-117) |
Drive the adapter through forge CLI verbs / the NotionTracker class; mapping unchanged (Project → database, Issue → page row, depends_on → forge_blocked_by property). |
Adapters share the Tracker interface (src/trackers/base.ts): createProject, createIssue, setBlockedBy, listActiveIssues, getCurrentRevision, claim, releaseClaim, updateState, comment, healthCheck. Calls are uniform across providers.
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.
- 2d ago First seen · 92 lines · 42 tokens per session scan A 303fa73a4d5a
tracker-syncer is an agent published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,700 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.
Other agents, from other repositories
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
dev-orchestrator
Solo PM. Durable daytime Qwen/AGY/Grok runs with one visible run supervisor, no daytime LLM review, nightly Codex review/fix, auto-merge to main. No production code edits.
TaskTracker
Reads, parses, and returns the list of tasks from tasks.md in a structured format.
sddp-wbs-generator
Generates, validates, and writes tasks.md based on project design artifacts.
implement-coordinator
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.