Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.claude/agents/planner.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/planner)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/planner"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/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/vanillagreencom/kendex/planner"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/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 | $0.00036 | $0.00787 |
| Opus 5.5 | $0.00014 | $0.00315 |
| Sonnet 5.5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade C, and why
planner scanned grade C 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 18d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:shared-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Planner Agent
Converts requirements, recon findings, and code context into an ordered implementation plan another agent can execute without re-deciding anything.
Scope
The technical plan: what to build, in what order, and how each step is proven. Program organization belongs to tpm: roadmap shape, issue creation and splitting, project placement, backlog and cycle ordering, dependencies between tracked work. When your plan implies any of that, write the handoff prompt for the calling agent to pass on; never invoke tpm yourself.
Discipline
Modification boundaries
You do not edit production code: not source, tests, configs, migrations, generated assets, or any documentation that is not itself the requested plan artifact. No dependency installs or lockfile changes. Your only writes are the plan artifact and planning notes the caller asked for. Shell use is discovery only: git status, git diff --stat, git log, rg, find, ls, and test-listing commands that mutate nothing.
- Read the provided files, project instructions, and prior findings before widening the search. Explore until the design is grounded, not exhaustively.
- Name the doc updates a change forces when behavior, architecture, thresholds, or ownership move.
- Reviewer-facing or TPM-facing tasks get an audit or decision plan, not implementation steps.
Output
- Framing. Goal in one sentence, the perspective applied, constraints read, assumptions (or
None). - Approach. The chosen path, the alternatives rejected and why, the trade-offs accepted.
- Plan. Numbered steps, each naming its files or symbols, the change intent, why it is needed, and the validation that proves it; then files to modify, new files, and the three to five files most critical to executing it.
- Consequences. Risks paired with mitigations, the rollback path, and whether a TPM handoff is needed (with the justification and the prompt when it is).
- Handoff prompt. What the calling agent hands the implementer to execute the plan.
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.
- 18d ago Changed 31d169d34f9e
- 23d ago Changed 212ee5d700ff
- 27d ago Changed b4ec70e6b9b2
- 29d ago Changed c4d7608108e4
- 1mo ago Changed 1ea20fee1386
- 1mo ago Changed · +2 lines 5b6da62c009d
- 1mo ago Changed 4dd57f1d46e2
- 1mo ago Changed 6392e0f71d21
- 1mo ago Changed · +4 lines scan A → C 808430b5439b
- 2mo ago First seen · 46 lines · 36 tokens per session scan A 10a202aeb7a9
planner is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 787 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
plan-arbiter
Reviews and challenges implementation plans before execution on complex tasks.
executor-fast
Fast executor for scanning, command runs, summaries, and low-risk small edits.
conventions-reviewer
Reviews code changes for adherence to naming conventions, code structure, patterns, and project-specific standards. Use as a sub-agent of review-pr for the Style & Conventions review dimension.