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 skills/obsfx/trekker-claude-code/task-syncnpx skills add obsfx/trekker-claude-code --skill task-syncgit clone --depth 1 https://github.com/obsfx/trekker-claude-codeWhat 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 | $0.00023 | $0.00602 |
| Opus 5 | $0.00012 | $0.00301 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
task-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 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Synchronization: Trekker is Primary
CRITICAL: Trekker is the PRIMARY task tracker. TodoWrite is secondary.
Trekker persists across sessions in SQLite. TodoWrite only lives within a conversation. When they conflict, Trekker wins.
The Rule
Trekker = Source of Truth (survives context resets)
TodoWrite = Session Mirror (conversation-scoped only)
Automatic Sync Behavior
When Starting a Session
- Read Trekker state first:
trekker --toon task list --status todo,in_progress - Populate TodoWrite from Trekker tasks
- Never trust TodoWrite from previous sessions - always refresh from Trekker
When Creating Tasks
1. Create in Trekker FIRST:
trekker task create -t "Title" -d "Description"
2. THEN mirror to TodoWrite:
TaskCreate with same subject
When Updating Tasks
1. Update Trekker FIRST:
trekker task update TREK-n -s in_progress
2. THEN update TodoWrite:
TaskUpdate for corresponding todo
When Completing Tasks
1. Add summary comment to Trekker:
trekker comment add TREK-n -a "claude" -c "Summary: ..."
2. Mark complete in Trekker:
trekker task update TREK-n -s completed
3. Mark complete in TodoWrite:
TaskUpdate status: completed
Priority Order
| Scenario | Action |
|---|---|
| Trekker has task, TodoWrite doesn't | Add to TodoWrite |
| TodoWrite has task, Trekker doesn't | Create in Trekker first |
| Both have task, states differ | Trekker wins, update TodoWrite |
| User creates via TodoWrite | Immediately create in Trekker |
Why Trekker is Primary
- Persistence: Survives context resets, TodoWrite doesn't
- Searchable:
trekker searchfinds past work - Auditable:
trekker historyshows change trail - Dependencies: Trekker tracks task relationships
- Multi-session: Work continues across conversations
Implementation Pattern
Before ANY task operation, think:
1. Is this in Trekker? → trekker task show <id>
2. Make change in Trekker FIRST
3. Mirror to TodoWrite AFTER
4. If conflict → Trekker wins
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 · 95 lines · 23 tokens per session scan A ec203333efca
task-sync is a skill published in the GitHub repository obsfx/trekker-claude-code (4 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 602 once invoked, about $0.0001 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.
Other skills, from other repositories
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
triage
Work-unit triage for GitHub issues. Groups raw issues, fuses each group with the AGENTS.md northstar, and externalizes each routed unit to a substrate record a collaborator session is pointed at.
create-issue
Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue — "file a ticket for this", "open an issue", "write this up for the backlog", "we should track this", "log this bug", "spec this out as a ticket so we can pick it up later" — i.e.…
forgecad-build-model
Build or edit a manufacture-realistic .forge.js model in a project, then validate it with run, render, inspect, and export evidence.
forgecad-design-spec
Create a ForgeCAD design brief, HLD, or LLD before coding by walking through use, assembly, interfaces, decisions, and verification.
forgecad-grade-model
Grade a ForgeCAD or CAD-as-code model against a requirement, brief, prompt, reference, or acceptance criteria with evidence and a 0-10 score.