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 agentmods add skills/lukasrepublic/agentic-foundry/id-documentnpx skills add lukasrepublic/agentic-foundry --skill id-documentgit clone --depth 1 https://github.com/lukasrepublic/agentic-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/id-document)<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/id-document"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/id-document.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 | $0.00269 | $0.03475 |
| Opus 5 | $0.00134 | $0.01737 |
| Sonnet 5 | $0.00054 | $0.00695 |
| Haiku 4.5 | $0.00027 | $0.00347 |
Grade A, and why
id-document 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 3d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
id-document — generate/update the change documentation from the recorded plan step-report note (infra-delivery step 16)
The infra-delivery step sequence (a documented procedure this skill family forms — no workflow engine or state-machine file ships) drives an infra change → merge. id-document is the documentation
step (step 16). It is a doc-output PROCEDURE skill the generic agent runs to generate or
update the change documentation a delivered IaC change requires — the change-record (an ADR: what
changed + why), the blast-radius summary, the runbook, the rollback note, and the
changelog entry — DERIVED from the recorded pre-merge plan step-report note + the plan summary
and MATCHED to the surrounding repo's existing doc conventions (where docs live, the changelog
format, the ADR style). It reads the recorded plan observation as DATA and produces docs; it
NEVER mutates infra, re-runs the plan, edits any verdict, or flips the workflow's
document step.
ADVISORY — not a gate, read-only, derived-from-recorded-evidence (the safety invariant)
This skill is ADVISORY, read-only, and derived-from-recorded-evidence. It is a
mistake-catcher FOR the trusted operator — it surfaces a missing change-record / stale runbook /
absent rollback note / changelog-convention mismatch. It does NOT gate, approve, merge, or block;
the merge floor (the adopter's branch protection + CI checks — see docs/merge-floor.md)
remains the only merge authority. Honest disclosure: earlier design intent had a FROZEN
contract + derive_infra_walk_verdict decide whether a change is safe to deliver at a dedicated merge
gate — that machinery was retired and does not exist in scripts/ today.
id-document issues no mutating verb. It does not re-run the plan, does not apply,
reconcile, or revert, does not decide a verdict, and does not flip the workflow's document
step. The docs are generated from the already-recorded plan observation read as DATA — the
recorded note is consumed, never re-run or mutated (id-document reads the recorded model, it never re-derives it).
Because this step runs no plan and produces no plan_results, its own output is a .foundry/
doc step-report note (the advisory .foundry/id-document-report record) — NOT walk-evidence,
NOT a verdict input, and carrying no machine-adjudicated GREEN claim (the binding rule:
advisory PROCEDURE steps record a step-report note; the bespoke pre-merge plan recorder
emit_infra_walk_evidence this note is sometimes contrasted against does not exist in scripts/).
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.
- 3d ago First seen · 175 lines · 269 tokens per session scan A 329b47eccc66
id-document is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed yesterday), licensed MIT. It adds 269 tokens to every session and 3,475 once invoked, about $0.0013 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
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
office-word
Use the bundled Office tools as the default path. Do not install OfficeCLI or document libraries when these tools are available.
moai-workflow-docs-claim-check
Read-only check of whether the claims a public-facing document makes (README, release notes, install and usage guides) are supported by user-supplied evidence. Runs Preflight, Claim Triage, and Validation, splits composite claims into atomic ones, and labels each. Runs no commands and writes no fixes.
pptx-maker
Generate or restyle a PowerPoint deck. Use when the user wants to create or edit a .pptx presentation, build slides from text or a URL, or design a reusable slide style.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…