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 davidmigloz/ai_clients_dart --skill releasegit clone --depth 1 https://github.com/davidmigloz/ai_clients_dartWrote 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/davidmigloz/ai_clients_dart/release)<a href="https://agentmods.dev/skills/davidmigloz/ai_clients_dart/release"><img src="https://agentmods.dev/badge/skills/davidmigloz/ai_clients_dart/release/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/davidmigloz/ai_clients_dart/release"><img src="https://agentmods.dev/badge/skills/davidmigloz/ai_clients_dart/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 303 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 312 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 305 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 315 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 337 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00063 | $0.07179 |
| Opus 5 | $0.00032 | $0.03589 |
| Sonnet 5 | $0.00013 | $0.01436 |
| Haiku 4.5 | $0.00006 | $0.00718 |
Grade A, and why
release 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 — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill for ai_clients_dart
This skill handles the full release lifecycle for the ai_clients_dart monorepo.
It supports three execution modes controlled via $ARGUMENTS:
/release --plan— Plan-only mode: detects changes, computes bumps, shows release plan. No file edits, no publish, no tags. Safe to run on any branch./release --dry-run— Dry-release mode: does everything including file edits anddart pub publish --dry-run, but stops before actual publishing/tagging/committing. Always restores the working tree before exit (on both success and failure)./release— Full release mode: the complete workflow.
Parse $ARGUMENTS to determine the mode. If $ARGUMENTS contains --plan, run in plan-only mode. If it contains --dry-run, run in dry-run mode. Otherwise, run in full release mode.
Step 1: Validate Environment
Perform all applicable checks before proceeding. Fail fast with an actionable error message if any check fails.
- Branch check (full release mode only):
Must be on
mainbranch. In--planand--dry-runmodes, any branch is allowed (but warn the user that results may differ from main).git branch --show-current # must output "main" in full release mode - Clean working tree: No uncommitted changes.
git status --porcelain # must be empty - Up-to-date with remote (full release mode only):
Ingit fetch origin main test "$(git rev-parse HEAD)" = "$(git rev-parse origin/main)" # HEAD must equal origin/main--planand--dry-runmodes, skip this check. - CLI availability:
dartandghmust be on PATH. - Auth preflight (skip in
--planmode):- GitHub:
gh auth status— must show authenticated. If not, tell user to rungh auth login. - pub.dev: There are two authentication mechanisms:
- OAuth session (from
dart pub login) — this is the primary and recommended method. It does NOT appear indart pub token list. - Token-based (from
dart pub token add) — these appear indart pub token listbut are less common.
- OAuth session (from
- Do not assume unauthenticated just because
dart pub token listis empty. An active OAuth session is invisible to that command. - Reliable verification: Run
dart pub publish --dry-runin any package directory as the auth smoke test. If it succeeds (exit code 0, no auth errors), authentication is working regardless of the mechanism.cd packages/{any_pkg} && dart pub publish --dry-run 2>&1 - If the dry-run fails with an authentication error, tell the user to run
dart pub login(OAuth, recommended) ordart pub token add https://pub.dev(token-based, alternative).
- GitHub:
What ships with it
3 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.
- 10d ago First seen · 519 lines · 63 tokens per session scan A b009a5aa22d6
release is a skill published in the GitHub repository davidmigloz/ai_clients_dart (24 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 7,179 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.