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 jasonm4130/claude-skills --skill plangit clone --depth 1 https://github.com/jasonm4130/claude-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/jasonm4130/claude-skills/plan)<a href="https://agentmods.dev/skills/jasonm4130/claude-skills/plan"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/plan/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/jasonm4130/claude-skills/plan"><img src="https://agentmods.dev/badge/skills/jasonm4130/claude-skills/plan.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 | $0.00183 | $0.01488 |
| Opus 5 | $0.00092 | $0.00744 |
| Sonnet 5 | $0.00037 | $0.00298 |
| Haiku 4.5 | $0.00018 | $0.00149 |
Grade A, and why
plan 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan by day
A plan is the only thing Nightshift reads. What this skill produces is read at 2 a.m. by a generator that cannot ask anyone anything, so every task must be complete on its own, and every open question must be closed before the plan merges. Announce: "Using nightshift:plan to turn this into a landable plan."
1. Size it, and stop early when you can
| Size | Looks like | Do |
|---|---|---|
| Trivial | one sitting, one file or one clear edit, no design choice | No artifact. Say so and do it now, or hand it to the user. |
| Medium | a few files, one design choice or none, a day's work | A lean plan: header, constraints, tasks. No spec. |
| Large | several subsystems, choices that are hard to reverse, more than a day | A short spec first (docs/specs/YYYY-MM-DD-<slug>.md: problem, decision, what is out), user-approved, then the plan. |
If the work spans independent subsystems, propose one plan per subsystem; each must produce working software on its own.
2. Settle the design, one question at a time
Read the code the change touches before asking anything. Then ask only what the code cannot answer, one question per turn, preferring multiple choice. State your interpretation and proceed when a wrong guess is cheap; ask when it is not. Two or three questions is typical; ten means the size was wrong.
HARD GATE: no implementation, no scaffolding, no "quick spike" before the user has approved the design (large) or the task list (medium). The loop lands what the plan says, so a plan written to a design nobody approved lands the wrong thing overnight.
3. Write the plan
Path: docs/plans/YYYY-MM-DD-<slug>.md (the repo's loop/config names the
plan being landed; a plan directory elsewhere wins if the repo already has one).
# <Feature> Implementation Plan
**Goal:** one sentence.
**Architecture:** two or three sentences on the approach.
**Tech Stack:** what the tasks use.
## Global Constraints
- one line each: version floors, naming rules, platform requirements.
Every task inherits these.
### Task 1: <component>
**Files:**
- Create: `exact/path.ts`
- Modify: `exact/existing.ts:120-140`
- Test: `tests/exact.test.ts`
**Interfaces:**
- Consumes: what this task uses from earlier tasks, exact names and types.
- Produces: what later tasks rely on, exact names and types.
- [ ] **Step 1:** write the failing test — show the test.
- [ ] **Step 2:** run it, expect FAIL with "<message>".
- [ ] **Step 3:** implement — show the code.
- [ ] **Step 4:** run `<the repo's test command>`, expect PASS.
- [ ] **Step 5:** commit: `git add <paths> && git commit -m "<why>"`.
## Open Questions
(must be empty before the plan merges)
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.
- 5d ago First seen · 112 lines · 183 tokens per session scan A 15e1572c1582
plan is a skill published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 183 tokens to every session and 1,488 once invoked, about $0.0009 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 2026-09-05.
Other skills, from other repositories
corpus
Worked examples of bad and corrected Claude Code chat output. Use when a reply is about to run long, when unsure whether a sentence is decoration or information, when a status update is forming, or when the user says the output is too long, too corporate, full of jargon, or reads like AI. Also use when writing or…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…