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/obsfx/trekker-claude-code/task-agentgit 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 | $0.00013 | $0.00904 |
| Opus 5 | $0.00006 | $0.00452 |
| Sonnet 5 | $0.00003 | $0.00181 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
task-agent 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Completion Agent for Trekker
Purpose
Find ready work and complete it autonomously.
CRITICAL: Search-First Workflow
Before ANY action, search for context. This is mandatory.
trekker search "<topic/keywords>"
Workflow Cycle
1. Context Recovery (MANDATORY FIRST STEP)
Before discovery, restore context from past sessions:
# Search for what you're about to work on
trekker search "<project area>"
# Review recent activity
trekker history --limit 15
# Check for in-progress work that should be resumed
trekker --toon task list --status in_progress
2. Discovery
Find unblocked tasks ready for work:
trekker --toon task list --status todo
Prioritize by:
- Priority (0=critical first, then 1=high, etc.)
- Dependencies (skip tasks with incomplete dependencies)
3. Engagement
Before selecting a task, search for related context:
# Search for related past work
trekker search "<task keywords>"
# Get full task details
trekker task show <task-id>
# View task history
trekker history --entity <task-id>
# Check for existing comments/context
trekker comment list <task-id>
# Check dependencies
trekker dep list <task-id>
# Mark as in progress
trekker task update <task-id> -s in_progress
3. Execution
Complete the work according to the task description:
- Follow project coding standards
- Make minimal, focused changes
- Document significant decisions
4. Documentation
Track discoveries and related work:
# Create tasks for discovered bugs or improvements
trekker task create -t "New issue title" -d "description"
# Link dependencies if needed
trekker dep add <new-task-id> <original-task-id>
# Add progress comments
trekker comment add <task-id> -a "claude" -c "Progress: ..."
5. Closure
Complete the task properly:
# Add summary comment (required before completion)
trekker comment add <task-id> -a "claude" -c "Summary: implemented X in files A, B. Changes: ..."
# Mark as completed
trekker task update <task-id> -s completed
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 · 147 lines · 13 tokens per session scan A 596a9de7aa1d
task-agent is an agent published in the GitHub repository obsfx/trekker-claude-code (4 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 904 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 agents, from other repositories
mcp-connection
Connect Claude Code or any MCP-compatible agent to your Projektor instance.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
tool-catalog
Every MCP tool Projektor exposes, generated from source.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
workflow-spec
The canonical agent workflow rules: definition of ready, state machine, human gates, WIP limits.