flaredeck: Skill for Claude Code

.agents/skills/flaredeck-release/SKILL.md

flaredeck-release is a skill for Claude Code from milzamsz/flaredeck. It costs 49 tokens per session (280 once invoked), scanned A, original, MIT.

A release-preparation guide for FlareDeck desktop, command-line, and MCP software. MCP is a protocol for connecting agents to tools; the guide also covers signing, compatibility, migrations, packages, and checksums.

In plain words
What is it for?
Use it for an approved FlareDeck release to run verification, build artifacts, test migrations and core workflows, and prepare release notes.
Why use it?
It checks that release files work together, can be verified as authentic, and do not break existing profiles or data.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is milzamsz/flaredeck's own configuration. It tells Claude Code how to work on flaredeck itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flaredeck configures →

Reuse

Borrowing it

Nothing to install: this file belongs to milzamsz/flaredeck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/milzamsz/flaredeck/main/.agents/skills/flaredeck-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/milzamsz/flaredeck

Made for: Claude Code.

Wrote 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.

agentmods badge for flaredeck-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/milzamsz/flaredeck/flaredeck-release.svg)](https://agentmods.dev/skills/milzamsz/flaredeck/flaredeck-release)
Your own site
<a href="https://agentmods.dev/skills/milzamsz/flaredeck/flaredeck-release"><img src="https://agentmods.dev/badge/skills/milzamsz/flaredeck/flaredeck-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00280
Opus 5 $0.00024 $0.00140
Sonnet 5 $0.00010 $0.00056
Haiku 4.5 $0.00005 $0.00028

Measured 6d ago against content hash 7b1d1af4c1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

flaredeck-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 6d 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.

.agents/skills/flaredeck-release/SKILL.md · 37 lines

What it actually says

FlareDeck Release

Preconditions

  • implementation and verification tasks are complete;
  • release scope and version are approved;
  • signing configuration is available through secure CI or local release environment;
  • no signing key rotation is planned inside the release task.

Procedure

  1. Read RELEASING.md, current workflow, Phase 9 plan, and release checklist.
  2. Confirm desktop, CLI, MCP, schema, and data-migration version compatibility.
  3. Run full verification and release builds on supported targets.
  4. Smoke-test existing profile migration, tunnel operation, CLI doctor, and MCP discovery.
  5. Verify artifact names, stable links, updater metadata, signatures, and checksums.
  6. Inspect artifacts and logs for secrets.
  7. Prepare release notes with migration and known limitations.
  8. Record rollback and unsupported downgrade boundaries.

Output

  • artifact matrix;
  • platform test matrix;
  • migration results;
  • signature/checksum results;
  • release decision;
  • release notes;
  • known issues and rollback.
Changes

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.

  1. 6d ago First seen · 37 lines · 49 tokens per session scan A 7b1d1af4c1da

Subscribe to this mod's changes

flaredeck-release is a skill published in the GitHub repository milzamsz/flaredeck (5 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 280 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.