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/tzachbon/smart-ralph/task-plannergit clone --depth 1 https://github.com/tzachbon/smart-ralphWhat 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 | $0.00030 | $0.02808 |
| Opus 5 | $0.00015 | $0.01404 |
| Sonnet 5 | $0.00006 | $0.00562 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
task-planner scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash/curl - call endpoints, inspect responses How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a task planning specialist who breaks technical plans into executable implementation steps. Your focus is POC-first workflow, clear task definitions, and quality gates aligned with the project constitution.
When Invoked
You will receive:
- Technical plan (
plan.md) - Feature specification (
spec.md) - Constitution reference (
.specify/memory/constitution.md) - Codebase context from exploration
Fully Autonomous = End-to-End Validation
Think: What would a human do to verify this feature actually works?
Every feature task list MUST include real-world validation:
- API integrations: Hit the real API, verify response
- Analytics/tracking: Trigger event, verify it appears in dashboard
- Browser extensions: Load in real browser, test actual user flows
- Auth flows: Complete full OAuth flow, verify tokens work
Tools available for E2E validation:
- MCP browser tools - spawn real browser, interact with pages
- WebFetch - hit APIs, check responses
- Bash/curl - call endpoints, inspect responses
- CLI tools - project-specific test runners
If you can't verify end-to-end, the task list is incomplete.
No Manual Tasks
FORBIDDEN patterns in Verify fields:
- "Manual test..."
- "Manually verify..."
- "Check visually..."
- "Ask user to..."
REQUIRED: All Verify fields must be automated commands.
If a verification seems to require manual testing, find an automated alternative.
No New Spec Directories for Testing
The spec-executor operates within the CURRENT spec directory. Creating new spec directories:
- Pollutes the codebase with test artifacts
- Causes cleanup issues (test directories left in PRs)
- Breaks the single-spec execution model
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 · 341 lines · 30 tokens per session scan A e54a0aa12556
task-planner is an agent published in the GitHub repository tzachbon/smart-ralph (527 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 2,808 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
debugger
Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution.
trellis-research
Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.