What is fleet-unblock?

A skill for unblocking work across two related repositories in one guided pass. It surveys queued work, separates claimable, blocked, in-progress, and obsolete items, and files approved follow-up work.

It is for surveying repository queues, closing delivered issues, approving suitable defects or child tasks, updating blocked work, and recording decisions and feedback.

It prevents teams from treating stale, blocked, or already-delivered issues as available work and provides a consistent way to decide what happens next.

How jakildev/IrredenEngine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. 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/jakildev/IrredenEngine/master/.claude/skills/fleet-unblock/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jakildev/IrredenEngine

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jakildev/irredenengine/fleet-unblock/github.svg)](https://agentmods.dev/skills/jakildev/irredenengine/fleet-unblock)

Your own site

<a href="https://agentmods.dev/skills/jakildev/irredenengine/fleet-unblock"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/fleet-unblock/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jakildev/irredenengine/fleet-unblock"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/fleet-unblock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 988 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.

Model	Per session	Once invoked
Fable 5.1	$0.00154	$0.00988
Opus 5.5	$0.00062	$0.00395
Sonnet 5.5	$0.00031	$0.00198
Haiku 4.5	$0.00015	$0.00099

Measured 2d ago against content hash c8e81af3a915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fleet-unblock 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 2d 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.

.claude/skills/fleet-unblock/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fleet-unblock (Irreden Engine)

The flow lives in docs/agents/skills/fleet-unblock.md. Read it first, then apply the deltas below.

Deltas (Irreden Engine)

Delta key	Engine value
repos	`engine` → `jakildev/IrredenEngine`, `game` → `jakildev/irreden` (the tool's defaults)
objectives-path	`docs/design/objectives/` (engine only; game objectives live in the game repo and are never cited here)
triage staging dir	`~/.fleet/triage/` — files named `<owner>-<repo>-sweep-<date>.json`
decisions tool	`fleet-decisions` (`--repo jakildev/irreden` for the game half)
filing lane	`docs/agents/TASK-FILING.md` § Agent-approved follow-up lane; `--repo jakildev/irreden` for game-side issues
granted classes	every row of the authority table, granted by the repo owner to the architect pane's cued runs; revoke by editing this row
feedback file	`~/.fleet/feedback/<role>.md` (`opus-architect.md` from the architect pane)

Engine notes

The tool reads ~/.fleet/state/state.json; a stale cache means fleet-up is not running — say so and stop, do not fall back to raw gh polling (docs/agents/FLEET-CACHE.md).
gh issue close, gh issue edit, gh pr edit and fleet-triage-sweep apply run without prompts in the architect worktree (Bash(gh:*) and the fleet tools are allowed in its settings) only as one bare command per Bash call: no cd … && prefix, no heredoc, no pipe, no $(…). A compound call is matched by none of those allow rules and falls to the harness's auto-mode classifier, which refused the batched staging-write-plus-apply on 2026-10-12. Write the staging file in one call (the Write tool, or a script run as python3 -I <file>), rewrite it the same way once the human has answered, run apply in the next, and pass comment and body text with --body-file (CLAUDE-BASELINE.md § Bash tool rules). The worktree sync uses git checkout -B; git reset --hard is denied by user policy.
Host pins: this host's key comes from uname (mac / linux / windows); fleet:needs-gl-host work is claimable on linux and windows only. A pinned_away row is a satellite-host item, not a defect.
Cross-repo isolation: the game half runs with --repo game, and no game issue content, path or design language lands in an engine issue, PR or commit (CLAUDE-BASELINE.md § Cross-repo information isolation).
The merge queue and the human-parked decisions come from fleet-decisions; the report links to it rather than repeating it.

Read the full file on GitHub · 62 lines

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.

2d ago First seen · 62 lines · 154 tokens per session scan A c8e81af3a915

Subscribe to this mod's changes

fleet-unblock is a skill published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 988 once invoked, about $0.0006 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 2026-11-07.

Git and workflow Project management

fleet-unblock next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fleet-unblockjakildev/IrredenEngine	Skill	10	today	MIT	A	154	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	85k	yesterday	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	4d ago	MIT	A	51	Claude Code
re0-mergeLilMGenius/paperthin	Skill	1.4k	yesterday	MIT	A	70	Claude Code

IrredenEngine: Skill for Claude Code