boss-whisperer

boss-whisperer is a skill for Claude Code from curiositech/some_claude_skills. It costs 149 tokens per session (1,451 once invoked), scanned B, original, MIT.

A workplace-communication analysis workflow that examines messages or a described situation involving a manager. It explains likely expectations, communication preferences, promotion context, and workplace politics without diagnosing the person.

In plain words
What is it for?
Use it to read email, Slack messages, performance reviews, or workplace situations and plan how to communicate with or manage up to a boss.
Why use it?
It helps make unclear management communication easier to interpret and keeps the analysis focused on understanding rather than manipulation. A deeper profile uses only publicly available research and requires opting in.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the boss-whisperer plugin — 1 skill shipped together

Good fit Use it to read email, Slack messages, performance reviews, or workplace situations and plan how to communicate with or manage up to a boss.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/boss-whisperer
Install

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.

Any agent
npx skills add curiositech/some_claude_skills --skill boss-whisperer
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

Or install boss-whisperer, the plugin that ships this one along with the rest of its 1 skill.

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 boss-whisperer

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/boss-whisperer/github.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/boss-whisperer)
Your own site
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/boss-whisperer"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/boss-whisperer/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 boss-whisperer

Your own site · 80×15
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/boss-whisperer"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/boss-whisperer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,451 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 84
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 30
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Output Handling · line 67
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
How audits are shown
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 $0.00149 $0.01451
Opus 5 $0.00075 $0.00726
Sonnet 5 $0.00030 $0.00290
Haiku 4.5 $0.00015 $0.00145

Measured 5d ago against content hash 6b207b2c27e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

boss-whisperer scanned grade B 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 5d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

transcript). Synthesise; never lecture. Mark inference as `(inference)`; absence of evidence is
.claude/skills/boss-whisperer/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boss Whisperer

Point a multi-framework profiling engine at your employer. Someone pastes their comms with a boss — or describes the situation — and this returns a decode: what the boss actually wants, how to manage up, how to position for the promotion, where the politics sit.

The brain is in FRAMEWORKS.md; the output contract is in DECODE-FORMAT.md. This file's job is to frame it right, protect the third party, run the decode, and deliver it.

When to Use

  • Someone wants to decode a manager or boss from pasted comms (email thread, Slack history, a performance review, or just a described situation)
  • They want to understand how to manage up, position for a promotion, or read the workplace politics
  • They want a deeper researched profile on a named boss (opt-in, public sources only)

Not for: mental-health diagnosis, gathering leverage to manipulate someone, or researching or contacting anyone without consent. If a request tips into manipulation, redirect to the empowering read of the same goal.

The line (read first, hold throughout)

Empowering, not manipulative. ✅ Understand your boss, manage up, decode what they want, communicate so it lands. ❌ Game them, exploit them, manufacture leverage, manipulate. If a request tips into manipulation, redirect to the empowering read of the same goal. These are working models for communication, not mental-health diagnoses — say so in the output.

Privacy by design (per-tier)

Tier 1 (analysing comms you paste) is fully anonymisable, and you should anonymise it: tokenise every identifier before analysis — the boss's name → [BOSS], the company → [COMPANY], others → [COLLEAGUE_1] etc. Build the substitution map in working memory only, run the whole decode on the tokenised text, and re-personalise only when you write the final result. Store nothing. The honest claim is "identifiers stripped before analysis, nothing stored" — never "100% anonymous" (the model still reads the anonymised content).

Read the full file on GitHub · 105 lines

Files

What ships with it

3 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.

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. 5d ago First seen · 105 lines · 0 tokens per session scan B 6b207b2c27e0

Subscribe to this mod's changes

boss-whisperer is a skill published in the GitHub repository curiositech/some_claude_skills (221 stars, last pushed 5d ago), licensed MIT. It adds 149 tokens to every session and 1,451 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.