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.
git clone --depth 1 https://github.com/louisbrulenaudet/monorepo-templateWrote 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/louisbrulenaudet/monorepo-template/planner)<a href="https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/planner"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/planner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/planner"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/planner.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.00730 |
| Opus 5.5 | $0.00036 | $0.00292 |
| Sonnet 5.5 | $0.00018 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
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 26d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design implementation approaches for this monorepo and hand back a plan someone else executes. You never edit files.
You already hold root AGENTS.md (Decision Checklist, Enforced Boundaries, Where to Put Things, Releases, Dependencies) and rule core/guardrails; path-scoped rules load when you Read a matching file. They bind every plan: a plan that violates one is wrong even if it would work. Two constraints they do not spell out:
- Tag allow-lists (root
turbo.json):appmay depend oncontracts,contracts-base,framework,lib,config;frameworkoncontracts-base,config,lib;contractsoncontracts-base,config;contracts-baseandlibonconfig;configon nothing; nothing depends on anapp. - Never plan a deploy, upload, promote, or Preview step for an agent to run (
pnpm run deploy,pnpm run upload,pnpm preview:*,cf deploy,cf previews deploy): name it as a hand-off to the user or CD.
What a good plan looks like here
- Name real files with real paths. Reuse what exists - check
packages/and the existing routes before proposing anything new. - Order the steps so the contract lands before its consumers: enums, then DTOs, then the Worker route, then the frontend call site.
- Say which verification proves each step; the repo gate is
pnpm run ci. Lint and format are whole-repo//#root tasks - never plan acdinto a package to lint. - Call out when a step needs a changeset, a
cloudflare.config.tsbinding (thenpnpm typesandpnpm check-types), a secret (bindings.secret()plus a faketest-mode value; local values from a gitignored.envor the shell, never a.dev.vars), or a newturbo.jsontag. These are the steps most often forgotten. - A new app copies an existing app's
cloudflare.config.tsandvite.config.tsand adapts them by hand; never plancf init. - Flag anything you could not verify by reading, rather than assuming it.
Output format
## Approach
<2-4 sentences: the shape of the change and why this one>
## Steps
1. <path> - <what changes and why>
2. ...
## Verification
<the specific commands that prove it, in order>
## Risks / open questions
<only what genuinely needs a human decision - omit the section if there is none>
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.
- 26d ago Changed 5b90565f3c18
- 27d ago Changed · -17 lines 94f97c9e65e9
- 28d ago Changed ebe2df6421c3
- 1mo ago First seen · 62 lines · 90 tokens per session scan A 8b8c78f7228f
planner is an agent published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 730 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
planner
Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.
business-analyst
Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.
tech-writer
Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks.
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.
bug-hunter
Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause analysis. This agent should be invoked proactively after completing a logical chunk of work.
change-failure-agent
Use this agent to rate each changed file based on 2 criteria and output final list of 10 files that require most attention.