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 rjroy/vibe-garden --skill update-evidencegit 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/skills/rjroy/vibe-garden/update-evidence)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/update-evidence"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/update-evidence/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/update-evidence"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/update-evidence.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 | $0.00059 | $0.00597 |
| Opus 5 | $0.00030 | $0.00298 |
| Sonnet 5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
update-evidence 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Evidence
Attach living implementation anchors to field-guide reference pages.
This is the mechanical pass between ingestion and semantic drift review:
ingestextracts durable knowledge from.lore/work/.update-evidenceconnects that knowledge to current code and tests.resolve-driftcompares the prose against those anchors.
Scope
Update indexed pages in .lore/reference/. Prefer .lore/reference/index.md; if it does not exist, read .lore/reference/index.html. Links may point to .md or .html pages.
Do not require fg-sources files to exist. Source artifacts are ingestion provenance and may be intentionally deleted after knowledge is extracted.
Evidence Metadata
For Markdown pages, add or refresh YAML frontmatter:
fg-evidence:
code:
- src/core/model/types.ts
tests:
- src/core/tests/model.test.ts
symbols:
- CardEffect
For HTML pages, add or refresh meta tags in <head>:
<meta name="fg-evidence-code" content="src/core/model/types.ts">
<meta name="fg-evidence-tests" content="src/core/tests/model.test.ts">
<meta name="fg-evidence-symbols" content="CardEffect">
How To Choose Evidence
Read the page body and identify concrete implementation claims:
- named modules, files, APIs, data files, and tests
- symbols in backticks
- world ids, feature ids, schema names, and settings keys
- statements about ownership, runtime flow, persistence, validation, UI behavior, or test coverage
Search the repository for those anchors with rg. Evidence should point to files that would naturally change if the page became stale.
Good evidence:
- code paths that implement the claim
- data files that contain the authored truth
- tests that assert the behavior
- stable symbols that should exist while the claim remains true
Weak evidence:
- files that only mention the same words incidentally
- generated artifacts
- stale work artifacts under
.lore/work/ - broad project files such as
package.jsonunless the page is specifically about tooling or stack choice
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.
- 12d ago First seen · 80 lines · 59 tokens per session scan A 01e387db6a5e
update-evidence is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 597 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.
Other skills, from other repositories
init-rpm
Project setup and verification. First run creates rpm context for a project. Repeat runs verify that an existing rpm setup matches the latest expected layout and apply safe migrations.
backlog
Manage the rpm backlog (long-term project tasks in docs/rpm/future/tasks.org — distinct from Claude's native TaskCreate list, which is session-scoped). Add, list, review, postpone, or complete entries. TRIGGER on natural-language backlog operations — phrasings like "backlog X", "add X to backlog", "add to backlog"…
version
Report the installed rpm plugin version. Use when the user asks for the rpm version, plugin version, installed version, or wants to verify which rpm release is loaded.
recursive-spine-digest
Use when sweeping all recursive-spine-conforming repos for tracking health — aging deferrals (oldest first), stalled milestones, in-flight by lane, assigned-but-untouched issues, and debts named in closing comments but never filed, plus seedling pollen that never transplanted (hive repos). Reports honest denominators…
recursive-spine-scaffold
Use when a repo has (or is getting) the tracking stamp and needs the rest of its spine — interviews for and stamps up to six parts, each optional: a rules codex with a moments map, an ADR directory, a CI gate skeleton, a session-memory convention, a constraints file with its sha-pinned drift gate, and the loop…
recursive-spine-bootstrap
Use when installing the recursive-spine tracking convention onto a repo — interviews for modules and dialect, then stamps labels, issue/PR templates, a CLAUDE.md/AGENTS.md tracking section, and cross-project board membership. Idempotent; degrades loudly on missing gh scopes; offers (never forces) plumb-line and…