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 lukasrepublic/agentic-foundry/plugin install foundryWrote 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/lukasrepublic/agentic-foundry/grounding-conformance)<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/grounding-conformance"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/grounding-conformance.svg" alt="Measured on agentmods" 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 | $0.00162 | $0.01915 |
| Opus 5 | $0.00081 | $0.00958 |
| Sonnet 5 | $0.00032 | $0.00383 |
| Haiku 4.5 | $0.00016 | $0.00192 |
Grade A, and why
grounding-conformance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/foundry:grounding-conformance
An operator/agent ADVISORY sweep that answers "how much of the frozen corpus is reality-grounded,
and which atoms are not?" — the coverage analogue of /foundry:drift-sweep (the batch sweep, which answers
a delta question: "did a schema change just invalidate frozen specs?"). This atom closes the
reality-grounding gate's retroactive gap: atoms authorized before the gate existed (the
system_grounding validators) carry no system_grounding block at all, so the corpus is only partially covered — this
sweep measures the gap and lists exactly the atoms that still need attention.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/foundry_grounding_conformance.py" \
--corpus-root "$CLAUDE_PROJECT_DIR" # default: $CLAUDE_PROJECT_DIR or cwd
# --snapshot /path/to/snapshot.json # optional: inject a pre-built system-state snapshot;
# default: build a fresh one host-side against --corpus-root
Input — the current system-state snapshot (host-side, HOW obtained is a wiring concern)
The engine entrypoint, foundry_grounding_conformance.classify_corpus(corpus_root, snapshot), takes
an already-built snapshot from the system-state snapshot tool (foundry_system_snapshot.build_system_snapshot() — {schema_ version, schema_grounded, module_grounded, grounding_configured, entities, modules, signature}) as a
parameter. It opens no grounding source itself. The standalone CLI above builds one fresh by
default (or accepts --snapshot for a pre-built/pinned one) — how the snapshot is obtained is the
caller's wiring concern, not the engine's.
The three-way classification (per atom, per the AC-GCB-1 normative rule)
For every frozen contract (carries an authorized: trailer — foundry_authz._authorized_block),
against the current snapshot:
- GROUNDED — carries a
system_groundingblock that passes structural validation (_system_grounding_structural_errors, zero errors) AND consistency validation (system_grounding_errors, zero errors vs. the snapshot). A well-formed emptyartifacts: []block is GROUNDED (conformant — nothing to ground). - UNGROUNDED — carries no
system_groundingblock at all (a pre-gate atom). - STALE — carries a block that is present but non-conformant: either structurally malformed (≥1 structural error — checked first, fail-safe) or contradicts the current snapshot (≥1 consistency error). A structurally malformed block is never silently GROUNDED — the consistency validator alone would skip it silently (it assumes the structural floor already ran), so both validators run, structural first.
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.
- 6d ago First seen · 117 lines · 162 tokens per session scan A 51fef226458c
grounding-conformance is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 1,915 once invoked, about $0.0008 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
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves GRAPHPROJECT, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
verify-findings
Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). Reads verifymanifest.json (written by stage22bverifyprepare), spawns one falsify-oriented verifier Task per toverify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel…
show-me-proof
증거줘. 증거줘. 테스트 로그, 변경사항, 완료 근거를 내.
ticket
Turn a note from the living manual (idea, feedback, or bug in a block, or a free-form report) into an actionable developer ticket with user stories, functional requirements, and acceptance criteria, plus open questions when completeness can't be verified. Syncs the manual's queue index and, when a tracker is…
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…