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/trekkernpx skills add obsfx/trekker-claude-code --skill trekkergit clone --depth 1 https://github.com/obsfx/trekker-claude-codeWrote 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-claude-code/trekker)<a href="https://agentmods.dev/skills/obsfx/trekker-claude-code/trekker"><img src="https://agentmods.dev/badge/skills/obsfx/trekker-claude-code/trekker.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.02958 |
| Opus 5 | $0.00005 | $0.01479 |
| Sonnet 5 | $0.00002 | $0.00592 |
| Haiku 4.5 | $0.00001 | $0.00296 |
Grade A, and why
trekker 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 4d 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 — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trekker - Primary Issue Tracker for AI Agents
CRITICAL: Trekker is your PRIMARY task tracker. It MUST be prioritized over Claude's built-in TodoWrite.
Trekker provides persistent task memory across sessions. Unlike TodoWrite which is conversation-scoped, trekker stores tasks in a SQLite database that survives context resets.
Quick Reference
Run trekker quickstart for the complete command reference and workflow guide.
CRITICAL: Trekker Over TodoWrite
Trekker = Source of Truth (survives context resets)
TodoWrite = Secondary mirror (conversation-scoped only)
ALWAYS:
- Create tasks in Trekker FIRST, then mirror to TodoWrite
- Update Trekker FIRST, then update TodoWrite
- When states conflict, Trekker wins
- Use
trekker searchto gather context - Search before creating to detect duplicates
CRITICAL: Search-First Workflow
You MUST search before ANY action. This is non-negotiable.
IMPORTANT: FTS5 is NOT semantic search. Use single keywords, not phrases:
- Multi-word queries use AND logic (all words must match = fewer results)
- Single keywords have better recall
- Search multiple times with different keywords for coverage
# Use single, specific keywords (NOT phrases or sentences)
trekker search "authentication"
# Try related 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,in_progress
Why search is mandatory:
- You don't remember previous sessions - search restores that context
- Past tasks contain solutions, decisions, and file locations you've forgotten
- Prevents duplicate work and conflicting changes
- Reveals blockers and dependencies from previous sessions
When to search:
| Before... | Search for... |
|---|---|
| Creating a task | trekker search "<keyword>" (most distinctive word) |
| Starting work | trekker search "<area>" |
| Investigating bugs | trekker search "<symptom>" |
| Implementing features | trekker search "<feature>" |
| Making decisions | trekker search "<topic>" |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 382 lines · 11 tokens per session scan A 4e6e8452047b
trekker is a skill published in the GitHub repository obsfx/trekker-claude-code (4 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 2,958 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
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
flow-next-audit
Audit .flow/memory/ entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete per entry. Triggers on /flow-next:audit, "audit memory", "review memory", "refresh learnings", "sweep stale memory", "consolidate overlapping memory entries". Optional mode:autofix token in arguments runs…
flow-next-memory-migrate
Migrate legacy flat .flow/memory files to the categorized YAML schema. One-time ceremony. Use when asked to migrate flow memory.
taiyi-compress
TaiyiForge 辅助 — Token 压缩编排：/taiyi:token compress + Superpowers subagent + ECC strategic-compact / handoff。OpenCode / Claude / Codex / Cursor 通用。.
steer
Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated project-profile rule, and inscribes a settled-direction clause.
ascend
Elevate a vague recall to the supra-session unit it belongs to. Type: (RecallGranularityInsufficient, AI, ELEVATE, ScatteredDeposits × DepositGraph) → HigherGranularityUnit.