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 skills add curiositech/some_claude_skills --skill boss-whisperergit clone --depth 1 https://github.com/curiositech/some_claude_skillsWrote 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.
[](https://agentmods.dev/skills/curiositech/some_claude_skills/boss-whisperer)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00149 | $0.01451 |
| Opus 5 | $0.00075 | $0.00726 |
| Sonnet 5 | $0.00030 | $0.00290 |
| Haiku 4.5 | $0.00015 | $0.00145 |
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 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).
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.
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.
- 5d ago First seen · 105 lines · 0 tokens per session scan B 6b207b2c27e0
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.