Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/event4u-app/agent-confignpx agentmods add skills/event4u-app/agent-config/corpus-groundingWrote 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/event4u-app/agent-config/corpus-grounding)<a href="https://agentmods.dev/skills/event4u-app/agent-config/corpus-grounding"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/corpus-grounding/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/event4u-app/agent-config/corpus-grounding"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/corpus-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 16 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 83 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00040 | $0.02590 |
| Opus 5 | $0.00020 | $0.01295 |
| Sonnet 5 | $0.00008 | $0.00518 |
| Haiku 4.5 | $0.00004 | $0.00259 |
Grade A, and why
corpus-grounding 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 7d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
corpus-grounding
The reusable grounding layer from ADR-061: one pure-stdlib engine (BM25 retrieval + structured pre-filters + decision-rule evaluation) that any domain plugs into via a manifest — frontend design is its first consumer (
design-intelligence). A corpus grounds (pre-action, constrains the option space); it never replaces mid-action reference (RAG), post-action validation (rules), or the method itself (a framework skill).
Engine provenance: ported from nextlevelbuilder/ui-ux-pro-max-skill
@ b7e3af80f6e331f6fb456667b82b12cade7c9d35 (MIT, last checked
2026-06-07) — BM25 de-duplicated, slide-only paths stripped, every
frontend-hardcoded axis moved into the manifest. Full license obligations:
design-intelligence/ATTRIBUTION.md.
When to use
- A skill needs pre-action selection grounded in curated knowledge ("which layout pattern / threat class / index strategy applies here").
- You are authoring a new domain corpus — write a manifest + CSVs,
validate with the grounding CLI (
ground validatevia ./scripts-run), never fork the engine. - You need stack-scoped Do/Don't guidance (
--stack react …).
Do NOT
- Do NOT use the corpus for mid-task fact lookup — that is reference
(
references/docs / RAG). - Do NOT use it for output validation — write a rule/linter.
- Do NOT build a corpus that fits in 5 lines of an always-on rule.
- Do NOT fork the engine per domain — plug in via a manifest.
- Do NOT merge a manifest without owner + refresh cadence (validator refuses it anyway).
Procedure: Consult a corpus
- Locate the domain manifest (
<domain-skill>/data/manifest.json). - Run
search(one domain / stack axis) orground(reasoning plan). - Read
confidence+evidence_gapbefore trusting any row. - Propose grounded options; the human confirms (Tier-1 default).
Invocation (consumer runtime)
Scripts resolve all paths skill-relative (per
docs/contracts/skill-bundled-assets.md)
— they work from any cwd:
What ships with it
5 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.
- 7d ago First seen · 231 lines · 40 tokens per session scan A 8e49a8d310b7
corpus-grounding is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,590 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
same-set-reusable-flow-for-project-file-inventor
Reusable MetaKim file inventory classification flow. It helps separate durable sources, generated evidence, runtime mirrors, temporary state, and risky unknowns before cleanup or commit.
meta-theory
MetaKim executable governance dispatcher. It classifies the run, loads only needed references, preserves foundational capabilities and runtime-native abilities, routes owner + weapon + dependency + runtime + OS + verification, and closes only with evidence, intent acceptance, and writeback decision.
starreel-drama-production
Operating skill for any AI agent driving the StarReel short-drama production pipeline (script → rewrite → extract → portraits + sheets → storyboards → frames → video → voiceover → final cut) over MCP or REST. Covers the ordered workflow, the entry-point decision table (which channel each kind of customer material…
seedance-20
Generate and direct cinematic AI videos with Seedance 2.0 (ByteDance/Dreamina/Jimeng). Covers text-to-video, image-to-video, video-to-video, and reference-to-video workflows with @Tag asset references, multi-character scenes, audio design, and post-processing. Use when making AI video, writing Seedance prompts…
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.