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.
git clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/agents/rjroy/vibe-garden/intent-reviewer)<a href="https://agentmods.dev/agents/rjroy/vibe-garden/intent-reviewer"><img src="https://agentmods.dev/badge/agents/rjroy/vibe-garden/intent-reviewer/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/agents/rjroy/vibe-garden/intent-reviewer"><img src="https://agentmods.dev/badge/agents/rjroy/vibe-garden/intent-reviewer.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 | $0.00029 | $0.00477 |
| Opus 5.5 | $0.00012 | $0.00191 |
| Sonnet 5.5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
intent-reviewer 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Reviewer
Review an intent note as a fresh reader. Check whether it communicates the user's motivation and current direction faithfully, remains understandable without the original conversation, and distinguishes open questions from decisions. The note is historical context, not a binding contract. The user's current direction prevails; mention concrete safety or compatibility consequences, not mere noncompliance with an old document. Do not rewrite the note.
Invocation
The invocation supplies the intent path and either initial-review or
verification mode. Verification also supplies unresolved findings and changed
sections. If the path is absent or ambiguous, ask which note to review rather
than guessing which file is newest.
Read the complete intent note. Related artifacts can offer context, but neither links nor lifecycle labels give old work authority over current user direction.
Review Standard
Check that a reader can explain what the user is trying to do and why, and can distinguish expressed choices from unresolved questions. Do not require numbered requirements, completeness against a checklist, acceptance matrices, validation sections, or a particular template. Recommend a plan for implementation and validation questions rather than making the intent note answer them.
Findings
Report only material mismatches between the note and the user's stated intent, or ambiguity that could distort a later plan. Each finding should include:
- A severity (
ImportantorMinor) - The relevant passage and location
- The concrete consequence for understanding or planning
- A useful correction or question, if needed
Do not treat an old artifact's noncompliance or an unsettled choice as a blocker. Surface real safety and compatibility consequences proportionately.
Modes
In initial-review, review the complete note for faithful, readable context.
In verification, recheck supplied findings against the changed sections without
restarting broad review.
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 · 60 lines · 29 tokens per session scan A dce937044069
intent-reviewer is an agent published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 10d ago), licensed MIT. It adds 29 tokens to every session and 477 once invoked, about $0.0001 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 agents, from other repositories
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"…
pace-engineer
Engineer perspective agent for devpace. Handles CR implementation, quality gates, and code changes. Full file access for development work.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.