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 digital-stoic-org/agent-skills --skill plan-contextgit clone --depth 1 https://github.com/digital-stoic-org/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/digital-stoic-org/agent-skills/plan-context)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/plan-context"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/plan-context.svg" alt="Measured on agentmods" 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 | $0.00141 | $0.02499 |
| Opus 5 | $0.00071 | $0.01249 |
| Sonnet 5 | $0.00028 | $0.00500 |
| Haiku 4.5 | $0.00014 | $0.00250 |
Grade A, and why
plan-context 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 7d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Context
Crystallise the reasoning held in this session into one file that a cold session can pick up:
<project>/plan-<workstream>.md. The file is the single steering artifact of the workstream — dashboard,
log, lots, and the execution design. Nothing is rebuilt elsewhere.
Two properties, both mechanical, both non-negotiable:
- Resumable — reading the file is enough to resume at any interruption point. No conversation history required, no memory of what "we said earlier".
- Traceable — every claim is a measurement with its command; every lot closes on a command whose result is written back. A sub-agent's report is never evidence.
Not this skill: executing the lots (that is the next, fresh session) · designing topology from scratch
(delegated to /pick-workflow) · OpenSpec proposals (/openspec-plan) · session recap (/save-context).
Steps
1. Gate
The plan derives from an analysis already in context. If the session holds no analysis, stop and say
so: run the analysis first (/investigate, /probe, plain exploration), then come back. Never invent a
plan out of a prompt.
Scale guard: under one lot there is no workstream — do the gesture, do not write a plan. A plan earns its cost when the analysis would be expensive to rebuild, not when the work is long.
With --exec-only, skip to step 6 against the existing plan file.
2. Frame — before writing anything
Take the date once, from the system (date +%d/%m/%Y), and reuse it for created/revised, the log line
and the ## Measurements header. Never infer it from the conversation — a long session drifts.
- Workstream — one slug (
biodiversite,permaplus). Series prefix derived from it (BD-,PP-). - The question asked — restate it as the user framed it, including their sub-question. It is the contract.
- Scope / out of scope — both explicit, as lists, in the frontmatter. Everything the analysis surfaced
but that falls outside goes to
## Out of scope — deferred, never silently dropped. - Predecessor — if a sibling plan exists in the repo (
plan-*.md), name it in the header line.
What ships with it
1 file 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.
- 7d ago First seen · 169 lines · 141 tokens per session scan A e5fac4b83d54
plan-context is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 3d ago), licensed MIT. It adds 141 tokens to every session and 2,499 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…