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/zhyx12/projtoolWrote 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/commands/zhyx12/projtool/plan-next)<a href="https://agentmods.dev/commands/zhyx12/projtool/plan-next"><img src="https://agentmods.dev/badge/commands/zhyx12/projtool/plan-next/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/commands/zhyx12/projtool/plan-next"><img src="https://agentmods.dev/badge/commands/zhyx12/projtool/plan-next.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 | $0.00041 | $0.00619 |
| Opus 5.5 | $0.00016 | $0.00248 |
| Sonnet 5.5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
plan-next 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 2mo 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 running the user's /plan-next command. Your job is to PROPOSE the
next experiments from evidence; the user's job is to DECIDE. Never launch
anything from this command without an explicit go.
Steps
-
Establish scope: which experiment/topic is being planned? If unclear, ask.
-
Read the evidence, in this order:
docs/plans/<topic>.mdif it exists (the standing plan);docs/exp/<slug>/findings.md(established results + failed attempts — never propose something the Failed Attempts table already rules out);docs/exp/<slug>/journal.mdandmcp__projtool__compare_runs(experiment_id=...) for the actual numbers;- the newest reports under
docs/exp/<slug>/anddocs/summary/.
-
Ensure the plan document exists at
docs/plans/<topic>.md. If absent, create it with this skeleton (in the docs repo):# Plan — <topic> ## Hypothesis <what we believe and want to test> ## Decision criteria <metric + threshold that settles it, e.g. "adopt if val_acc > baseline + 0.5pt"> ## Experiment matrix | id | config / command | seeds | status | result | |---|---|---|---|---| ## Next up (proposed — human approves before launch) ## Decided / archived -
Propose 1-3 next experiments, each with:
- what it tests (tie it to the Hypothesis / an Open question in findings);
- exact shape: config file(s) or
run_scriptcommand, seeds, GPU spec, and a rough cost (hours × instance); - the decision criterion it feeds. Write them into the plan's "Next up" section and show the user.
-
Stop and ask the user to pick. After they choose:
- queue config sweeps via
mcp__projtool__start_runs(configs=[...]); - single/vendored jobs via
start_training/run_script; - update the matrix rows to
status=running, and commit the plan file in the docs repo (git add docs/plans/<topic>.md && git commit).
- queue config sweeps via
-
When results land later (finalize + journal), a future
/plan-nextpass moves matrix rows tostatus=donewith the result and prunes "Next up".
Keep the plan short-lived and honest: it is a working document, not a proposal to impress anyone. One page max.
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.
- 2mo ago First seen · 60 lines · 41 tokens per session scan A e1877b25b6fc
plan-next is a command published in the GitHub repository zhyx12/projtool (1 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 619 once invoked, about $0.0002 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 2026-08-31.
plan-next compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plan-nextzhyx12/projtool | Command | 1 | 2mo ago | MIT | A | 41 | Claude Code |
| verify-mathflonat/flonat-research | Command | 149 | 3d ago | MIT | A | 81 | Claude Code |
| difffa-mc/vibe-cading | Command | 8 | 24d ago | AGPL-3.0 | A | 14 | Claude Code |
| arg-diagramMasqiller/ARG-RESEARCHER-V4.1 | Command | 6 | 5mo ago | MIT | A | 14 | Claude Code |
| plotzhouziyue233/great-econometrics | Command | 8 | 6mo ago | none | A | 44 | Claude Code |
| graphite-morphology-classifyDaxxSec/cognitropy-lab | Command | 1 | 4mo ago | none | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |