grimoire-construct-update

grimoire-construct-update is a skill for Claude Code from ojCezarFerreira/Grimoire. It costs 65 tokens per session (2,219 once invoked), scanned A, original, MIT.

A development workflow that moves tasks from a written specification to a plan and then implementation, with a faster route for small changes. It also records status, requires tests before code, and coordinates helper agents.

In plain words
What is it for?
Use it to manage software features, write tests first through test-driven development, split work among helper agents, and record changes with focused commits.
Why use it?
It keeps requirements, planning, tests, commits, and progress in a consistent structure instead of relying on informal notes.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the grimoire plugin — 11 skills shipped together

Good fit Use it to manage software features, write tests first through test-driven development, split work among helper agents, and record changes with focused commits.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ojCezarFerreira/Grimoire
Claude Code
/plugin install grimoire

Made for: Claude Code.

Or install grimoire, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for grimoire-construct-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-construct-update.svg)](https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-construct-update)
Your own site
<a href="https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-construct-update"><img src="https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-construct-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02219
Opus 5 $0.00032 $0.01110
Sonnet 5 $0.00013 $0.00444
Haiku 4.5 $0.00006 $0.00222

Measured 8d ago against content hash 40afd27ade7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grimoire-construct-update 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 8d 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.

skills/grimoire-construct-update/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[Required Reading]

  1. Read ${CLAUDE_PLUGIN_ROOT}/GRIMOIRE-CONVENTIONS.md. The sections that apply to this skill are: § Construct (the single source of truth for the construct artifact — definition, folder layout, CONSTRUCT.md format, writer contract, and the Alteration rules subsection that governs every in-place change), § .grimoire/ layout (the constructs/ folder structure), § Sub-agent spawning (research for add/edit operations runs in sub-agents; the orchestrator stays lucid and owns the interview, resolution, and writes), § Skill composition, § Commits (the docs(grimoire): update construct <name> commit), § User-facing language, § Pause-point pattern (the resolution hard-stop, the locked-[specced] refusal, the clarifying-questions / operation-selection pause, and the draft-review pause), § Project context (read PROJECT.md; never write it), and § IDE-aware review (the draft surface). Not applicable: § TDD, § Historic, and the Spec → Plan → Execute page lifecycle do not apply — this skill is orthogonal (same family as grimoire-init / grimoire-note / grimoire-construct) and is the construct analog of grimoire-note: it writes no page, no SPEC.md, and no HISTORIC.md entry. Do not restate any § Construct / Alteration rule in this body — reference it.
  2. If .grimoire/PROJECT.md exists in the project root, read it for project context. If it does not exist, proceed without it and, at the end of the run, give the non-blocking reminder to run grimoire-init once (per § Project context).
  3. If .grimoire/HISTORIC.md exists, read it read-only for recent-page recency context. Absence is non-blocking — this skill does not write or depend on HISTORIC.md.

[Objective] Alter an existing construct in place per the § Construct Alteration rules: add, remove, or reorder references in the [pending] tail, refine a [pending] reference's detail, rewrite the construct intro/objective, or rename the construct (preserving NNN). The construct is the roadmap-of-record; this skill keeps it accurate without ever spawning a page or disturbing the work already specced.

User's target + requested alteration:

$ARGUMENTS

[Hard constraints — orthogonal skill]

  • Never write to .grimoire/HISTORIC.md. Never write to .grimoire/PROJECT.md. Never create a page folder under .grimoire/pages/.
  • Never create a construct — bringing a construct into existence belongs to grimoire-construct. This skill only alters one that already exists, and hard-stops otherwise (see Phase 1).
  • The [specced] prefix is immutable and the construct stays flat and self-contained — these are the § Construct Alteration rules and self-containment guarantees; do not restate them here, enforce them.

[Phase 1: Target Resolution & Precondition Check (HARD STOP)] Resolve the user's input to an existing .grimoire/constructs/NNN-<name>/ folder — by the NNN number or by the <name>. List .grimoire/constructs/ and match. If the target does not exist, STOP immediately, creating or changing nothing, with the canonical message from § Pause-point pattern:

❌ Construct NNN does not exist. Run /grimoire-construct first.

Do not offer to run grimoire-construct automatically; do not create the folder. Once resolved, read CONSTRUCT.md and identify the locked [specced] prefix (the leading 1..k references, lowest-numbered) versus the [pending] tail (k+1..n). Every alteration in the following phases is confined to that pending tail (or to construct-level metadata), per § Construct Alteration rules.

[Phase 2: Research (conditional)] For add/edit operations that need codebase or external grounding (e.g. a new reference whose shape depends on how the project is structured, or a refined detail that must reflect an established external convention), spawn research sub-agent(s) per § Sub-agent spawning so the orchestrator's context stays lucid. Equip each sub-agent with Read, Grep, Glob, read-only Bash, and — when the alteration's shape depends on facts outside the repo — WebSearch / WebFetch. The sub-agent returns its findings plus an explicit list of anything it was uncertain about (these become questions for Phase 3). For pure structural operations (remove, reorder, rename) that need no grounding, skip this phase — do not spawn a sub-agent gratuitously.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 8d ago First seen · 71 lines · 65 tokens per session scan A 40afd27ade7f

Subscribe to this mod's changes

grimoire-construct-update is a skill published in the GitHub repository ojCezarFerreira/Grimoire (2 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 2,219 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens