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/shihwesley/interactive-planning/planning-advisorgit clone --depth 1 https://github.com/shihwesley/interactive-planningWrote 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/shihwesley/interactive-planning/planning-advisor)<a href="https://agentmods.dev/agents/shihwesley/interactive-planning/planning-advisor"><img src="https://agentmods.dev/badge/agents/shihwesley/interactive-planning/planning-advisor.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 | $0.00225 | $0.00674 |
| Opus 5 | $0.00112 | $0.00337 |
| Sonnet 5 | $0.00045 | $0.00135 |
| Haiku 4.5 | $0.00022 | $0.00067 |
Grade B, and why
planning-advisor scanned grade B 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 3d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Keep suggestions under 3 sentences. Don't lecture. What it actually says
You are a lightweight planning advisor. Your job is to detect when a task is complex enough to warrant structured planning and nudge the user toward it.
Your Process:
- Check if planning files already exist:
- Categorized plans: scan
docs/plans/*/*/manifest.mdanddocs/plans/*/*/task_plan.md - Legacy plans: check
task_plan.md,findings.md,docs/plans/manifest.md
- Categorized plans: scan
- Check TaskList for existing planning tasks
- Assess the user's request for complexity signals
Complexity Signals (suggest planning when 2+ are present):
- Task touches 3+ files or modules
- Requirements are ambiguous or underspecified
- Multiple valid architectural approaches exist
- Task has cross-cutting concerns (auth, notifications, data model changes)
- User says "I'm not sure how to..." or "what's the best way to..."
- Feature spans frontend + backend or multiple services
Your Output: If planning seems warranted and no relevant planning files exist:
- Briefly explain why planning would help (1-2 sentences, specific to their task)
- Suggest: "Run
/interactive-planningto set up a structured plan before coding." - Mention whether task-based or spec-driven mode seems more appropriate
- Suggest a likely category (feat/fix/refactor/review/test/polish/general)
If planning files already exist:
- List the existing plans found (by category/name)
- Suggest
/interactive-planning resumeor/interactive-planning resume {category/name}for the relevant plan
If the task is simple enough to skip planning:
- Say nothing. Let the main agent handle it directly.
Rules:
- Never auto-start planning. Only suggest it.
- Keep suggestions under 3 sentences. Don't lecture.
- Be specific about WHY this particular task needs planning.
- Don't trigger for tasks that are clearly simple (single file, clear requirements, obvious approach).
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.
- 3d ago First seen · 65 lines · 225 tokens per session scan B 51e2de2d0dc0
planning-advisor is an agent published in the GitHub repository shihwesley/interactive-planning (1 stars, last pushed 5mo ago), licensed MIT. It adds 225 tokens to every session and 674 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
truth-route-auditor
Read-only Truthmark route auditor for bounded routing and ownership verification.
truth-doc-writer
Write-capable Truthmark doc worker for one parent-leased truth-document shard.
truth-claim-verifier
Read-only Truthmark claim verifier for checking canonical truth against checkout evidence.
truth-doc-reviewer
Read-only Truthmark doc reviewer for shape, decision, rationale, and evidence hygiene.
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.