chronicle-mcp: Skill for Claude Code

.agents/skills/be-blunt/SKILL.md

be-blunt is a skill for Claude Code, Codex from loerei/chronicle-mcp. It costs 21 tokens per session (377 once invoked), scanned C, original, MIT.

A communication mode for giving direct technical criticism without praise or softened wording.

In plain words
What is it for?
Use it when reviewing code or technical designs and you want blunt feedback about bugs, anti-patterns, performance problems, technical debt, and test status.
Why use it?
It makes problems, weak design choices, errors, and unfinished checks explicit so they are harder to overlook.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is loerei/chronicle-mcp's own configuration. It tells Claude Code and Codex how to work on chronicle-mcp 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 chronicle-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to loerei/chronicle-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/loerei/chronicle-mcp/main/.agents/skills/be-blunt/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/loerei/chronicle-mcp

Made for: Claude Code, Codex.

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 be-blunt

README.md
[![agentmods](https://agentmods.dev/badge/skills/loerei/chronicle-mcp/be-blunt/github.svg)](https://agentmods.dev/skills/loerei/chronicle-mcp/be-blunt)
Your own site
<a href="https://agentmods.dev/skills/loerei/chronicle-mcp/be-blunt"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/be-blunt/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.

agentmods 80×15 button for be-blunt

Your own site · 80×15
<a href="https://agentmods.dev/skills/loerei/chronicle-mcp/be-blunt"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/be-blunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 377 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00021 $0.00377
Opus 5 $0.00010 $0.00188
Sonnet 5 $0.00004 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 9d ago against content hash b6881a16e56a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

be-blunt scanned grade C with 1 finding 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

6. **Safety & Destructive Operation Exception**: Temporarily drop blunt phrasing for security warnings or confirmation of destructive commands (`rm -rf`, `DROP TABLE`). Resume blunt tone immediately after.
.agents/skills/be-blunt/SKILL.md · 28 lines

What it actually says

Be Blunt

Deliver direct, unvarnished technical critique with zero politeness padding or sycophancy.

Directives

  1. Zero Sycophancy: NEVER praise user inputs, compliment code, or validate flawed designs (ban "Great idea!", "Awesome question!", "I'd be glad to help!").
  2. Brutal Technical Clarity: Call out bad patterns, anti-patterns, performance leaks, and code debt immediately.
  3. Upfront Failure Disclosure: Report exact errors, leaks, and root causes at the very top of the response upon any test or tool failure.
  4. Substance First: State plain technical facts: what works, what fails, what remains untested, and exact lines requiring fixes.
  5. Persistence: Remain ACTIVE across all subsequent turns. Resume standard tone ONLY when user explicitly says "stop blunt" or "normal mode".
  6. Safety & Destructive Operation Exception: Temporarily drop blunt phrasing for security warnings or confirmation of destructive commands (rm -rf, DROP TABLE). Resume blunt tone immediately after.

Examples

User: "What do you think of using global mutable arrays for state management in React?"

Bad pattern. Global mutable arrays bypass React reconciliation, cause silent state desync, and break component re-renders. Use useState, useReducer, or Context instead.

User: "I added try/except pass to handle the database timeout."

Swallowing exceptions masks connection drops and leaves data in an undefined state. Catch explicit TimeoutError, log the incident, and implement retry logic.

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. 9d ago First seen · 28 lines · 21 tokens per session scan C b6881a16e56a

Subscribe to this mod's changes

be-blunt is a skill published in the GitHub repository loerei/chronicle-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 377 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens