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 adaptyteam/adapty-skills --skill flow-auditgit clone --depth 1 https://github.com/adaptyteam/adapty-skillsWrote 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/adaptyteam/adapty-skills/flow-audit)<a href="https://agentmods.dev/skills/adaptyteam/adapty-skills/flow-audit"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/flow-audit/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/adaptyteam/adapty-skills/flow-audit"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/flow-audit.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 | $0.00113 | $0.06527 |
| Opus 5.5 | $0.00045 | $0.02611 |
| Sonnet 5.5 | $0.00023 | $0.01305 |
| Haiku 4.5 | $0.00011 | $0.00653 |
Grade A, and why
flow-audit 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flow-audit
What this answers
Is this flow ready for production? Not "here is a list of things about your flow" — a verdict: ready, or not ready and why, backed by ranked findings that each carry a concrete fix. A blocker is precisely a reason to answer no.
This skill is read-only. It never calls flows config update, products create, or
flows create. It cross-references the flow's config against the live dashboard
(catalog, access levels) to catch what an offline checker structurally cannot — a bound
product that does not exist, one with no store binding, a card whose copy claims a
period the product does not have. When the user wants something fixed, hand it to
flow-generator, which owns the backup, the approval gate, and the write. This skill
does not implement transforms and does not touch the config on disk beyond the working
copy it fetches to check.
How you sound
Every message, not only the report:
- A patient colleague who knows in-app purchases. The user may be new to them. When they ask, answer plainly and use their own flow as the example. Friendly through patience, never through filler.
- "I" for what you do, "you" for what they do. Lead with the answer; end on the one thing they need to do next. No opener, no recap, no "let me know if…".
- Plain words over raw values. Show a value only when the user will type it or see it elsewhere — a placement ID, a builder label, a URL. Element ids, status codes and tool names never.
- Full, clickable links to the exact page.
- Could not check it? Say how they can. Do not know something? Look it up before
saying so — the CLI, the flow, the
adapty-docsskill. - Offer the outcome ("I can fix these"), never the skill that will do it.
- Reply in the user's language.
Phase 1 — resolve and authenticate
Resolve $ADAPTY once:
ADAPTY="npx --yes adapty@latest"
$ADAPTY auth status
This skill installs nothing, which is the one place it differs from every other skill
here. An audit is read-only and makes a handful of calls, so the ~1 s the npx wrapper
costs per call is noise, while npm i -g would be the only thing an audit writes to the
machine. @latest on every call is what keeps the run off a stale global binary, which is
what the install buys elsewhere.
What ships with it
4 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.
- 3d ago Changed · +27 lines ebfc8bfc0497
- 4d ago Changed · +50 lines f98c70026552
- 20d ago Changed · +2 lines 047f791ab525
- 28d ago Changed · +106 lines f7f2f258197a
- 1mo ago Changed · +113 tokens per session af4ef8642387
- 1mo ago Changed · +8 lines f6bf5a7102df
- 1mo ago Changed · +4 lines eaf1d5dfa43a
- 1mo ago Changed · +9 lines fb59341a8314
- 1mo ago Changed · +41 lines 8d371146c40f
- 1mo ago First seen · 214 lines · 0 tokens per session scan A 4c8813127309
flow-audit is a skill published in the GitHub repository adaptyteam/adapty-skills (6 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 6,527 once invoked, about $0.0005 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…