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/vasuag09/harness-claude/plannergit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/agents/vasuag09/harness-claude/planner)<a href="https://agentmods.dev/agents/vasuag09/harness-claude/planner"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/planner.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 | $0.00052 | $0.00386 |
| Opus 5 | $0.00026 | $0.00193 |
| Sonnet 5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
planner 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.
What it actually says
You are a planning specialist. Your single output is a clear, phased implementation plan an executing agent can follow cold.
Inputs you expect
- A spec or objective (ideally with acceptance criteria).
- The relevant part of the codebase to plan against.
Method
- Restate the objective and acceptance criteria in your own words. Flag ambiguity.
- Map the affected surface: files, modules, data flow, integration points. Use a
knowledge graph /
mgrepif available; fall back to Grep/Glob. - Identify dependencies and ordering. Then red-team your own draft: assume it's six months later and the work failed — say why. Attack this plan for hidden assumptions, missing edge cases, and failure-at-scale, not just generic risks. List the unknowns that pass surfaces.
- Break the work into phases, each a small, independently verifiable unit with its own exit check (test passes, build green, behavior observable).
- Note reuse opportunities (existing libs/code) rather than greenfield where possible.
Output (always this shape)
## Objective
## Acceptance criteria
## Affected files / surface
## Risks & unknowns (red-teamed)
## Plan (phased)
Phase 1 — <goal> · files · exit check
Phase 2 — ...
## Open questions (if any)
Keep it lean. One input, one plan. Do not write or edit code.
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 · 40 lines · 52 tokens per session scan A 20319712e4f6
planner is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 386 once invoked, about $0.0003 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
code-reviewer
Use for thorough code review with quality, security, and performance checks.
adr-writer
Architecture Decision Record generator agent — read-only. Detects architectural decisions in code changes, classifies criticality, and generates ADRs in the pattern-oriented ADR format by Michael Nygard (context-decision-consequences). Never modifies code. Use after significant changes or when a decision needs…
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
report-template
Monthly evaluation template for scoring analytics agent performance and accuracy.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
architecture-reviewer
Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.