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 joshuadavidthomas/agent-skills --skill roadmap-to-improve-plansgit clone --depth 1 https://github.com/joshuadavidthomas/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/joshuadavidthomas/agent-skills/roadmap-to-improve-plans)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/roadmap-to-improve-plans"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/roadmap-to-improve-plans/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/joshuadavidthomas/agent-skills/roadmap-to-improve-plans"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/roadmap-to-improve-plans.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 | $0.00088 | $0.01543 |
| Opus 5 | $0.00044 | $0.00772 |
| Sonnet 5 | $0.00018 | $0.00309 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
roadmap-to-improve-plans 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap to Improve Plans
Turn selected strategic-roadmap opportunities or accepted feature slices into grouped batches of numbered improvement plans. This is the wide planning stage: preserve the audit judgment, feature decisions, and architecture diagnosis behind each selected item, then turn it into enough detail for future executors to work safely.
Treat plan writing as meta-work: the output should improve future execution loops by carrying forward impact, risk, confidence, design claims, regression checks, approval boundaries, and STOP conditions.
This owns this pipeline's NNN plan-bank contract directly.
Source Frame
Before writing plans, load what applies:
- The selected
.agents/ROADMAP.mdor equivalent roadmap/opportunity artifact. - Accepted feature-planning artifacts when splitting a feature outline or final plan into PR-sized improvement plans.
improvefor the original audit posture: category, evidence, impact, effort, risk, confidence, fix sketch, and “not worth doing” verdicts.- The
coding-standardsskill as the canonical source for standards concerns. Load only the reference files matching the selected work; do not copy the standards into this skill or the plan. improve-codebase-architecturefor architecture/deepening candidates: current friction, shallow-module diagnosis, deletion test, locality/leverage, and recommendation strength.- DLS-style exemplar plans when present in the target repo, especially effort indexes, numbered plans, memos, rejected/deferred notes, and reconciliation logs.
- Project docs and commands:
AGENTS.md,README.md,CONTEXT.md, architecture docs, ADRs, package/test config, CI config, and current VCS state.
Workflow
- Select plan scope
- Start from selected roadmap items, accepted feature artifacts, or ask the user which items to plan.
- Treat one effort directory as one improvement batch: one theme, one outcome, one README index.
- Split unrelated projects, features, or outcomes into separate batches.
- Preserve dependency order from the roadmap or feature outline; do not flatten everything into parallel tasks.
What ships with it
4 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.
- 12d ago First seen · 100 lines · 88 tokens per session scan A 67c2ffb07fe3
roadmap-to-improve-plans is a skill published in the GitHub repository joshuadavidthomas/agent-skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,543 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…