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 lukasrepublic/agentic-foundry --skill id-promotegit 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-promote)<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/id-promote"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/id-promote.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 | $0.00485 | $0.04970 |
| Opus 5 | $0.00243 | $0.02485 |
| Sonnet 5 | $0.00097 | $0.00994 |
| Haiku 4.5 | $0.00049 | $0.00497 |
Grade A, and why
id-promote 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 8d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
id-promote — the cross-env promotion orchestrator (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 IaC change → realized infrastructure, per environment.
Step 16 id-promote is the promotion procedure: "this change passed in env N — carry it to env
N+1 (e.g. staging→prod)." It is ADVISORY orchestration — it defines NO new verdict of its
own. It RE-RUNS the existing per-env change-delivery loop in the target environment, composing
the already-shipped primitives over the next env's gitops class and binding, then proves
the change LANDED in the target env through the post-deploy realization frame.
A change green in staging is NOT auto-green in the next environment. The merge floor (the
adopter's branch protection + CI checks — see docs/merge-floor.md) re-derives at the promotion
merge into the target env, the realization verdict re-derives landing per env, and id-apply's
decide_apply — re-derived against the target environment's own change scope and infra_binding —
decides the apply. id-promote REFLECTS each of those re-derivations; it never substitutes its
own assertion for any of them.
When to trigger
- The
infra-deliverysequence advances to the promotion step (step 16) — a change verified in env N is to be carried to env N+1 (staging→prod). - The operator says "
/foundry:id-promote", "promote this change to prod", or "run the promotion".
ADVISORY — this skill reflects the gate; it is NOT the merge authority and self-certifies NOTHING
This skill is an ADVISORY craft orchestrator + mechanical mistake-catcher FOR the trusted operator. It re-runs the existing per-env loop; it is NOT itself a new gate and adds NO new verdict. The authorities stay where they are:
- the realization verdict (
derive_realization_verdict— real, live) decides landed / not-landed per env; - the merge floor (the adopter's branch protection + CI checks + human review — see
docs/merge-floor.md) decides the promotion merge into the target env's branch; id-apply'sdecide_applydecides whether and how each environment's apply runs, against the AWS context the operator has configured for that environment.
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.
- 8d ago First seen · 234 lines · 485 tokens per session scan A 9d78c850234e
id-promote is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 3d ago), licensed MIT. It adds 485 tokens to every session and 4,970 once invoked, about $0.0024 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
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
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.
merge
Merge the reviewed pull request for the current branch, then hand straight off to cleanup. A sentence of editorial direction alongside the green light is read as a rider. Use when a human green-lights an open PR.
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.