A coordination workflow for running a group of builders in tmux, a terminal tool that keeps several sessions visible at once. It covers checking readiness, sending briefs, watching progress, and closing the work.

Use it to start and supervise a builder wave, relay updates, and finish the wave with its provided scripts.

It gives a repeatable way to manage several builders instead of tracking each one manually. It also keeps launch, progress updates, and completion steps from being missed.

How retospect/precis-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to retospect/precis-mcp. 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/retospect/precis-mcp/main/.claude/skills/gripe-fleet/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/retospect/precis-mcp

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/retospect/precis-mcp/gripe-fleet/github.svg)](https://agentmods.dev/skills/retospect/precis-mcp/gripe-fleet)

Your own site

<a href="https://agentmods.dev/skills/retospect/precis-mcp/gripe-fleet"><img src="https://agentmods.dev/badge/skills/retospect/precis-mcp/gripe-fleet/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/retospect/precis-mcp/gripe-fleet"><img src="https://agentmods.dev/badge/skills/retospect/precis-mcp/gripe-fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,786 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 unknown 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	$0.00067	$0.04786
Opus 5.5	$0.00027	$0.01914
Sonnet 5.5	$0.00013	$0.00957
Haiku 4.5	$0.00007	$0.00479

Measured today against content hash b2e8f93d8207, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gripe-fleet 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 today.

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/gripe-fleet/SKILL.md · 228 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

today Changed · +18 lines b2e8f93d8207
2d ago Changed · +5 lines · +4 tokens per session d300badd6085
4d ago Changed 71cdfad1a982
5d ago Changed · +7 lines a8cf9fc95877
6d ago Changed · +13 lines 86720d3e270b
10d ago Changed · -3 lines · +22 tokens per session scan B → A 7662b07753d3
11d ago Changed · +60 lines scan A → B 50903e6c8cce
13d ago Changed · +7 lines aec07fdfb30b
14d ago Changed · +5 lines beacaa248773
16d ago First seen · 116 lines · 41 tokens per session scan A c80fdbf932da

Subscribe to this mod's changes

gripe-fleet is a skill published in the GitHub repository retospect/precis-mcp (11 stars, last pushed today), licensed GPL-3.0. It adds 67 tokens to every session and 4,786 once invoked, about $0.0003 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 2026-10-15.

LLM Project management Python ai-agent mcp mcp-server model-context-protocol

gripe-fleet next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gripe-fleetretospect/precis-mcp	Skill	11	today	GPL-3.0	A	67	Claude Code
swagjmagar/swag-mcp	Skill	7	4d ago	MIT	A	118	Claude Code
quantum-vqexi-zhao/OpenQuantum	Skill	71	yesterday	MIT	A	53	Claude Code, Codex
quantum-vqlsxi-zhao/OpenQuantum	Skill	71	yesterday	MIT	A	56	Claude Code, Codex
octave-chatterelevanaltd/octave-mcp	Skill	54	3d ago	Apache-2.0	A	64	Claude Code
@elad12390/web-research-assistantelad12390/web-research-assistant	Skill	9	9d ago	MIT	A	150	Claude Code, Codex
comparen24q02m/wet-mcp	Skill	17	1mo ago	Apache-2.0	A	15	Claude Code

precis-mcp: Skill for Claude Code