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 agentmods add skills/nirvaan05/bleu-plugin/bleunpx skills add Nirvaan05/Bleu-Plugin --skill bleugit clone --depth 1 https://github.com/Nirvaan05/Bleu-PluginWhat 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 | $0.00194 | $0.07942 |
| Opus 5 | $0.00097 | $0.03971 |
| Sonnet 5 | $0.00039 | $0.01588 |
| Haiku 4.5 | $0.00019 | $0.00794 |
Grade A, and why
bleu 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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bleu
Turn an idea into a fully thought-through, deeply structured system plan - from architecture down to file-level execution - before any code is written. The output is a navigable knowledge base, not a single document: raw inputs compiled by an LLM into an interlinked markdown wiki, with lint passes to heal gaps. No RAG, no vector store, no embeddings - the whole plan fits in a modern context window and every claim is traceable to a file a human can open, edit, or delete.
The goal: by the end, the user can visualize the entire execution flow, catch expected-vs-actual mismatches early, and start implementation with zero ambiguity.
Why this skill exists
Most "planning" with an LLM is one-shot: ask for an architecture, get a wall of text, lose it next session. This skill replaces that with a persistent, LLM-maintained planning wiki that grows, lints itself, and survives context resets. It's deliberately heavy on structure because the failure mode of light planning is discovering the architectural hole in week three.
The strongest single argument for the skill, worth memorizing:
The tedious part of maintaining a knowledge base is not the reading or the thinking - it's the bookkeeping. Updating cross-references, keeping summaries current, noting when new data contradicts old claims, maintaining consistency across dozens of pages. Humans abandon wikis because the maintenance burden grows faster than the value. LLMs don't get bored, don't forget to update a cross-reference, and can touch 15 files in one pass.
That's the bet. Every other design choice in this skill serves it. Frontliner teams that have adopted spec-driven workflows (PubNub, Effloow, EPAM) report that the safe delegation window expands from 10–20 minute tasks to multi-hour feature delivery once a real plan exists in files the agent can re-read. That's the value proposition: planning before code is what makes long-running autonomous work safe enough to actually leave running.
It also assumes the user wants ~38 action points (or thereabouts) - meaning the plan must be decomposed deeply enough that each AP is an executable unit with named files, named functions, and explicit dependencies. Anything vaguer than that and the skill isn't done yet. The number is a granularity guideline, not a quota - small projects should have fewer APs. The Phase 0 intake sizes the workflow to the project. Don't sledgehammer a nut.
What ships with it
8 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.
- references/action-point-template.md 5.9 KB
- references/advanced-architecture.md 44 KB
- references/claude-code-integration.md 35 KB
- references/handoff-formats.md 17 KB
- references/knowledge-base-pattern.md 14 KB
- references/landscape-research.md 63 KB
- references/research-and-citations.md 6.4 KB
- references/session-persistence.md 19 KB
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 · 288 lines · 194 tokens per session scan A 59332c7e8822
bleu is a skill published in the GitHub repository Nirvaan05/Bleu-Plugin (3 stars, last pushed 2mo ago), licensed MIT. It adds 194 tokens to every session and 7,942 once invoked, about $0.0010 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.
Other skills, from other repositories
vibeframe
Work through the VibeFrame project model — plan with vibecontext, declare intent with vibedeclare/vibedecide, bind implementations with vibelink, and resolve drift findings. Use when this project has a .vibeframe/ directory and you are planning a feature, implementing one, responding to a VibeFrame drift warning, or…
design-patterns
Rust design patterns for RTK. Newtype, Builder, RAII, Trait Objects, State Machine. Applied to CLI filter modules. Use when designing new modules or refactoring existing ones.
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.