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.
git clone --depth 1 https://github.com/obsfx/trekkerWrote 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.
[](https://agentmods.dev/commands/obsfx/trekker/create)<a href="https://agentmods.dev/commands/obsfx/trekker/create"><img src="https://agentmods.dev/badge/commands/obsfx/trekker/create/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.
<a href="https://agentmods.dev/commands/obsfx/trekker/create"><img src="https://agentmods.dev/badge/commands/obsfx/trekker/create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00010 | $0.00353 |
| Opus 5.5 | $0.00004 | $0.00141 |
| Sonnet 5.5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
trekker:create 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- trekker:create — 100% identical, 0 lines differ
What it actually says
Create a new task in trekker.
IMPORTANT: /trekker:create is a skill (invoke via Skill tool), NOT a bash command. Use trekker task create CLI as shown below.
MANDATORY: Search Before Creating
You MUST search before creating ANY task. This is non-negotiable.
# Search for existing/related issues FIRST
trekker search "<keywords from task title>"
trekker search "<related concepts>"
If search finds related issues:
- Consider updating the existing issue instead of creating a duplicate
- Add a comment to the existing issue if it needs more context
- Only create a new task if truly distinct from existing work
Interactive Flow
- Search for existing issues (MANDATORY - show results to user)
- If no duplicates found, ask for the task title (required)
- Ask for the task type context:
- Is this part of an epic? If so, which one?
- Ask for priority (0-5, default 2)
- Ask for description (STRONGLY encouraged - tasks without context are useless)
- Ask for tags (optional, comma-separated)
Execution
trekker task create -t "<title>" [-d "<description>"] [-p <priority>] [-e <epic-id>] [--tags "<tags>"]
After Creation
Show the created task details and ask if the user wants to:
- Start working on it immediately (set to in_progress)
- Link it to another task as a dependency
- Create a subtask
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.
- yesterday First seen · 47 lines · 10 tokens per session scan A 39b4dc2f0fad
trekker:create is a command published in the GitHub repository obsfx/trekker (84 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 353 once invoked, about $0.0000 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 2026-10-25.
Other commands, from other repositories
maintainer-standup
Synthesize the maintainer's morning standup brief from gathered git/PR/issue/state data.
answer
A build round is one archon-ship run on the item. Read how it ended and decide what the queue does next: the item is done, the queue continues it with another round, or a maintainer must decide. The next node performs what you declare and reads it back: it pushes commits the round left unpushed, records your decision…
route
Decide whether the build queue launches its next run on this item, and write the brief the run starts from. Triage already decided the route; you keep it thin. The next node performs what you declare: it launches archon-ship with your brief, raises your attention item, or takes an already finished pull request out of…
decide
This run's $INPUTS.stage stage has ended. Decide whether its ending already has a next step, or whether it stops where only a person can take it forward. When it stops, write the attention item that person answers. You read and decide only: the repository, the forge and the tracker stay exactly as you found them. The…
revisit
Intake recorded each item below as blocked: something had to happen first. Work lands in parallel, so a blocker can be resolved, superseded or made irrelevant while its issue is still open, and an item can stay blocked long after it could move. Judge, for each item, whether it still looks blocked now. You don't…
linear-cleanup
Audit Linear issues for problems (missing labels, stale, duplicates, wrong state, orphaned, unactionable) and propose fixes.