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 skills add obsfx/trekker --skill searchgit 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/skills/obsfx/trekker/search)<a href="https://agentmods.dev/skills/obsfx/trekker/search"><img src="https://agentmods.dev/badge/skills/obsfx/trekker/search/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/skills/obsfx/trekker/search"><img src="https://agentmods.dev/badge/skills/obsfx/trekker/search.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 | $0.00014 | $0.00532 |
| Opus 5.5 | $0.00006 | $0.00213 |
| Sonnet 5.5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
search 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:
- search — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Use This First
Search is your PRIMARY tool for gathering context.
Before starting ANY work:
trekker search "<single keyword>"
This finds related past work using FTS5 full-text search.
IMPORTANT: FTS5 is NOT Semantic Search
Trekker uses FTS5 full-text search, NOT semantic/AI search. This means:
- Use single, specific keywords - not phrases or sentences
- Multi-word queries use AND logic -
"fix authentication bug"requires ALL three words present, returning FEWER results - Search multiple times with different keywords for broader coverage
- Pick the most distinctive word from what you're looking for
| BAD (too many words) | GOOD (single keyword) |
|---|---|
trekker search "fix login authentication bug" |
trekker search "authentication" |
trekker search "user cannot access account" |
trekker search "account" |
trekker search "performance optimization slow" |
trekker search "performance" |
trekker search "deployment pipeline issues" |
trekker search "deployment" |
When to Use (ALWAYS)
- Before creating tasks - find existing work
- Before starting work - gather context
- When investigating issues - find related bugs
- When user describes problem - understand history
- When resuming work - recover context
Commands
# Search with a single keyword
trekker search "authentication"
# Try multiple keywords separately for broader coverage
trekker search "login"
trekker search "password"
# Filter by type
trekker search "deployment" --type task
# Filter by status
trekker search "memory" --status todo
# Rebuild index if needed
trekker search "caching" --rebuild-index
Workflow: Before ANY Task Operation
1. SEARCH: trekker search "<single keyword>"
2. BROADEN: Try 2-3 related keywords if first search has no results
3. REVIEW: Check if similar work exists
4. DECIDE: Update existing OR create new
5. SYNC: Mirror to TodoWrite after Trekker
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 · 77 lines · 14 tokens per session scan A 1114f2f4b75c
search is a skill published in the GitHub repository obsfx/trekker (84 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 532 once invoked, about $0.0001 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 skills, from other repositories
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
parallel-work-check
Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
issue-ingest
Full execution protocol for MODE: ISSUEINGEST -- GitHub issue intake, localization, spec generation, and transition to the full fix workflow.
phase-wrap
Claude Code adapter for MODE: PHASE-WRAP. Delegates to the canonical opencode-swarm phase boundary protocol.
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.