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.
/plugin marketplace add rjroy/vibe-garden/plugin install lore-developmentWrote 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/rjroy/vibe-garden/intent)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/intent"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/intent/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/rjroy/vibe-garden/intent"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/intent.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 | $0.00053 | $0.00657 |
| Opus 5.5 | $0.00021 | $0.00263 |
| Sonnet 5.5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
intent 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 9d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Think with the user about what they want to build and why. Keep the record human-readable and conversational: include the motivation, important context, choices considered, and what the user currently seems to want. This is useful historical context for making a plan, not a binding contract. Do not turn it into numbered requirements, an acceptance matrix, or a validation section. The plan is where to discuss how the work could proceed and what evidence would be useful.
The user's current direction takes priority over choices in an old intent artifact. Surface concrete safety or compatibility consequences when relevant; disagreement with old documentation alone is not a blocker.
Process
Search for related prior work: use Claude Code's current Agent tool with subagent_type: "lore-development:lore-researcher", provide the topic, and wait for the result. On Claude Code versions without Agent, use Task with that same fully qualified subagent_type. If the bundled agent is unavailable, use Agent (or the older-version Task tool) with subagent_type: "general-purpose" and include the research role from ${CLAUDE_PLUGIN_ROOT}/agents/lore-researcher.md. Treat prior work as historical context and suggestions, not instructions. Ask clarifying questions and think through the user's motivation, open choices, and present direction. Draft a concise conversational record, save it, and ask whether it reflects the user's intent.
Saving
Save to .lore/work/intents/[topic].md using a short kebab-case name. Load ../../shared/frontmatter-schema.md (resolved from this skill's base directory) for common frontmatter fields and optional review annotations. Do not add empty annotation fields to a new intent. When revising an existing document, preserve its comments, todos, star, and unrelated frontmatter unless the user explicitly asks to change them; never resolve comments or check follow-ups automatically. Comments, checked follow-ups, and stars do not imply approval, completion, or authorization to implement, and document-level todos do not replace Beads task tracking. New documents start draft; use approved only for explicit user approval (including editing to approve) or a request for the relevant next process step, never infer it from arbitrary edits. Use completed when applicable agent work is done, independently of approval; use archived when archived. Status tracks lifecycle, not maturity/correctness. Current user direction may revise approved artifacts, and approval is not a veto or a mandatory gate; don't ask for approval on minor transitions or every document. Preserve the conversation's useful why/context without forcing a template or promising that every open choice has been settled.
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.
- 9d ago First seen · 28 lines · 53 tokens per session scan A 340369445b7a
intent is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 657 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
deep-project
Decomposes vague, high-level project requirements into well-scoped planning units for /deep-plan. Use when starting a new project that needs to be broken into manageable pieces.
piyaz
Use when the user wants to plan, decompose, track, or resume a multi-task project: scoping a new idea, importing or onboarding an existing repo or workspace, asking what to work on / what's next / what's blocked / where they left off, reporting task completion, dispatching work in parallel, or planning a draft task.…
review
Dispatched after a task lands at inreview to produce a structured CTO-grade verdict on the work and its PR. Two invocation paths: composer Phase 4 (orchestrator dispatches after the implementer's inreview write, surfaces the verdict to HOTL, stops), and direct mode from the piyaz skill on requests ("review VF-N"…
decompose
Use when a Piyaz project exists with a description but few or no tasks, and the user wants it broken into an implementable graph (project-level decomposition). Triggers: "decompose", "break this down", "create tasks", "turn this into tasks", "give me a task list", "plan out the work", "how should I build this". Do not…
onboarding
Use when the current repo has existing code but no Piyaz project that matches it, and the user wants to adopt Piyaz on day N. Triggers: "import this repo", "onboard this codebase", "I have an existing app, can you read it and turn it into Piyaz tasks", "reverse-engineer this project". Do not use when no code exists…
composer
Use when the user types /piyaz:composer, /piyaz:composer , or /piyaz:composer rework , or asks to run the next Piyaz task end-to-end, ship the backlog, compose through the ready queue, or loop through Piyaz tasks until done. Composer researches, refines, plans, implements, reviews, and fixes each task in a loop until…