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 akka/ai-marketplace --skill conformgit clone --depth 1 https://github.com/akka/ai-marketplaceWrote 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/akka/ai-marketplace/conform)<a href="https://agentmods.dev/skills/akka/ai-marketplace/conform"><img src="https://agentmods.dev/badge/skills/akka/ai-marketplace/conform/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/akka/ai-marketplace/conform"><img src="https://agentmods.dev/badge/skills/akka/ai-marketplace/conform.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 | $0.00032 | $0.01238 |
| Opus 5 | $0.00016 | $0.00619 |
| Sonnet 5 | $0.00006 | $0.00248 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
conform 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
You MUST consider the user input before proceeding (if not empty).
Purpose
/akka:conform runs the in-scope auditors and reports whether the feature is
ready to ship. For every machine-checkable exit condition it runs the
condition's auditor — building, testing, linting, or probing as the check
requires — and resolves it to a state. It then prints the same manifest
/akka:status shows, and returns a verdict.
The verdict is assessed against the release tier, so it covers every applicable condition at every ship tier — not just the tier you happen to be shipping to next.
Two commands sit close to this one and are not it:
/akka:statusprints the same manifest but never runs an auditor. Status leaves machine-checkable conditionsopen; conform resolves them. Once conform has evaluated, the two agree./akka:convergediffs the codebase against the spec, plan, and tasks and queues unbuilt work. Conform evaluates the exit conditions and reports readiness. Neither substitutes for the other.
/akka:ship reads this same verdict — in Enforced mode it releases only when
the verdict is READY_TO_SHIP.
The verdict
READY_TO_SHIP— every applicable condition isgreenand not stale, or covered by an effective waiver.NOT_READY— any other combination.
A NOT_READY verdict says what is blocking and what to do about it:
- conditions
openwith reasonneeds-user-actionare waiting on the user; - conditions
openwith reasonblocked-outside-projectneed a tool or policy change beyond this project — never treat one as a failure the user caused; - stale greens need their auditor re-run.
Outline
-
Evaluate. Call
akka_ec_conformfor the project directory. This runs the available auditors and returns the manifest plus the verdict. It is the full CLI pipeline — org floor, project strikes, waivers, sign-offs, and mode — so it agrees exactly withakka specify conform.This is not a cheap call. It executes real builds and probes. Do not run it speculatively or in a loop; if the user only wants to see where things stand,
/akka:statusis the read-only view.
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.
- 10d ago First seen · 110 lines · 32 tokens per session scan A 943deeafefba
conform is a skill published in the GitHub repository akka/ai-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 1,238 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 2026-08-31.
Other skills, from other repositories
gsd-verify-work
Validate built features through conversational UAT.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
gsd-eval-review
Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.
gsd-validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase.
gsd-audit-uat
Cross-phase audit of all outstanding UAT and verification items.
tdd
Test-driven development with red-green-refactor loops around vertical slices (tracer bullets), not horizontal layers. Use when asked to "use TDD", "write test-first", "red-green-refactor", "build this with tests", or when a feature has a clear observable contract. The discipline complement to the test/add-tests skills…