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 skills add ParthGanatra/agent-skills --skill plangategit clone --depth 1 https://github.com/ParthGanatra/agent-skillsWrote 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/skills/parthganatra/agent-skills/plangate)<a href="https://agentmods.dev/skills/parthganatra/agent-skills/plangate"><img src="https://agentmods.dev/badge/skills/parthganatra/agent-skills/plangate/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/skills/parthganatra/agent-skills/plangate"><img src="https://agentmods.dev/badge/skills/parthganatra/agent-skills/plangate.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 | $0.00131 | $0.01898 |
| Opus 5 | $0.00066 | $0.00949 |
| Sonnet 5 | $0.00026 | $0.00380 |
| Haiku 4.5 | $0.00013 | $0.00190 |
Grade A, and why
plangate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlanGate — terminal-native plan-review loop
Batch the decisions into a reviewable plan file instead of forcing the user through
one-by-one chat. The user reviews in vim; their :w is the signal; you resolve and
revise; no code until it's agreed. Full background & prior art: see the repo README.
Review markers (the contract). Everything the user reviews is markdown blockquotes:
> Q:— a question / decision / anything needing the user's input. Whenever you write a> Q:line, put an empty> A:line directly under it so the user jumps in and types the answer with no marker typing (their vim has]ato jump to the next empty> A:and start typing).> A:— the answer. The user fills the empty slot; you fill it when replying to a> Q:the user raised.- An open item = an empty
> A:slot (^\s*> A:\s*$), plus any> Q:the user added with no> A:under it. The loop is done when every> Q:has a non-empty> A:beneath it. - Blockquotes keep the plan valid markdown (renders fine in Obsidian/GitHub) and — with the bundled
vim reading setup (see README) — highlight
> Q:vs> A:, with]q/[qto page between open questions.
Helper scripts live beside this file:
open-plan.sh <file>— open/focus the plan in a right-side vim pane (its own pane; never hijacks the user's working vim).wait-save.sh <file> [max_s]— block until the user saves; run it in the BACKGROUND so their:wre-invokes you.nudge-reload.sh— after you edit the plan, refresh the user's vim (:checktime+ autoread) to show your> A:answers.prune-plans.sh <plans-dir> [days]— delete plan files untouched for N days (default 7). Run it once per plan, at step 2.
When to fire
- 2+ open decisions/tradeoffs, or multiple implementation steps → propose the loop.
- One simple/single-answer question → just answer, no plan.
- If the user says "just answer" / "skip the plan" → drop the loop for that task.
Loop
- Scope it. Feature comes from the
/plangate <description>argument if given, else infer it from the conversation and confirm your one-line summary before writing.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 110 lines · 131 tokens per session scan A 0ae009b55e2e
plangate is a skill published in the GitHub repository ParthGanatra/agent-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 1,898 once invoked, about $0.0007 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 skills, from other repositories
superdesign
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants…
declauding
Removes LLM prose tics from drafts — staged reveals, "it's not X, it's Y", significance tags, abstraction agency, coy headers, fragment cadence, the flatter slop patterns (copula avoidance, participle tails, forced triads, chatbot residue), the flat-certainty patterns the pass itself produces (bare adverbs, juridical…
image-to-svg
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork…
declaring-invariants
Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use when reviewing tests, when a module…
developing-preact
Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON…
generative-thinking
Break out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, perspective shift, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations…