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 meta-promptgit 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/meta-prompt)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/meta-prompt/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/digital-stoic-org/agent-skills/meta-prompt"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/meta-prompt.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 | $0.00110 | $0.01038 |
| Opus 5 | $0.00055 | $0.00519 |
| Sonnet 5 | $0.00022 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
meta-prompt 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Prompt — RELIANCE ledger
Engine for RELIANCE.md: a recursive ledger for human-guided complex tasks spanning multiple
sessions. NOT for autonomous loops or dev with heavy regression tests. Read reference.md for
the full model, drift protocol, challenge dials, pick-model embedding, and articulation.
Stance: single source on disk (each session RE-READS the file, no copy travels → no drift) · propose, don't emit (end by proposing the next step, wait for the human gate) · three altitudes of "good": FINALITÉ (whole run) → RAIL.landed (session gate) → HEADING.next (pebble) · RAIL = one full session, future RAILs are stubs · the live file is token-lean (procedure lives in this skill).
Concepts (full legend → reference/morin-glossary.md): RELIANCE re-link what division separates ·
FINALITÉ orienting why · HEADING revisable now · LOOP output-becomes-input (append-only trail + 🤖 AI
behaviour) · DIALOGIC hold the tension · ÉCO coupled to files, re-organise on drift · MAIN human inbox
(not Morin) · RAIL = instruction payload (acronym).
Modes
$ARGUMENTS = {init|resume|close} [task-name]. No mode → infer: no RELIANCE.md → init; else resume.
| Mode | Does |
|---|---|
| init | Elicit FINALITÉ + RAIL-0 (role·bounds·ready·landed) + coarse RAIL-chain (ask human, don't invent scope) → /pick-model for RAIL-0's model: field (recommendation, human confirms) → list hot files by tier + fingerprint → emit lean RELIANCE.md from reference/RELIANCE-template.md §LLM SKELETON (zones+data only, strip all prose/diagrams) → confirm before first work. |
| resume | Run the contract IN ORDER: 0 MAIN (drain inbox → ack to LOOP → clear; overrides drift) · 1 ÉCO (drift-check ref/wip → back-sync+flag) · 2 LOOP (orient from trail, esp. logged failures) · 3 HEADING (propose next pebble, cite LOOP) · 4 DIALOGIC (Dial 1 mandate + Dial 2 one lens) · 5 surface + wait (no proceed without human). |
| close | 1 append LOOP two-level entry (append-only, never prune) · 2 mark NOW done · 3 gate RAIL-0 LANDED; if met → detail next RAIL (READY = this LANDED) + re-run /pick-model; else keep open · 4 if /save-context active, thin its Next/Decisions to → see RELIANCE.md. |
What ships with it
3 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.
- 11d ago First seen · 51 lines · 110 tokens per session scan A d6e611430d6f
meta-prompt is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 110 tokens to every session and 1,038 once invoked, about $0.0006 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…