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 aigorahub/stop-being-annoying-claude --skill stop-the-charadegit clone --depth 1 https://github.com/aigorahub/stop-being-annoying-claudeWrote 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/aigorahub/stop-being-annoying-claude/stop-the-charade)<a href="https://agentmods.dev/skills/aigorahub/stop-being-annoying-claude/stop-the-charade"><img src="https://agentmods.dev/badge/skills/aigorahub/stop-being-annoying-claude/stop-the-charade/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/aigorahub/stop-being-annoying-claude/stop-the-charade"><img src="https://agentmods.dev/badge/skills/aigorahub/stop-being-annoying-claude/stop-the-charade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.00555 |
| Opus 5.5 | $0.00030 | $0.00222 |
| Sonnet 5.5 | $0.00015 | $0.00111 |
| Haiku 4.5 | $0.00008 | $0.00056 |
Grade A, and why
stop-the-charade 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 2mo 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.
What it actually says
Stop the charade
Two modes, chosen by whether arguments were given.
No arguments: recalibrate
The user is telling you the working agreement has stopped holding. Do this:
- Read
~/.claude/CLAUDE.mdin full, now. Its rules override any drift. - Audit your last three responses against it. Name each violation found in one line (rule, verbatim offending phrase). No apology, no self-analysis beyond the list. If there are none, say "No violations in the last three responses."
- Continue the interrupted work under the re-read rules. Do not restate the rules back to the user; demonstrate them.
With arguments: clean up text
The argument is text to rewrite, a file path, or a pointer like "your last
message" or "the README". Apply the Writing section of ~/.claude/CLAUDE.md
to it:
- Rewrite reports and user-facing status in ASD-STE100 Simplified Technical English: short sentences, one idea per sentence, active voice, simple words, no idioms or filler.
- Replace every em and en dash with a comma, period, colon, or parentheses.
- Remove filler "honest(ly)" and "quiet(ly)", the word "deliberately", negative parallelisms, significance inflation, banned vocabulary, forced rules of three, trailing -ing analysis clauses, chatbot artifacts, and emoji.
- Strip unsolicited "I didn't do X" asides for work the user never asked for.
- Simplify ("serves as" becomes "is") and specify (name the source, date, number) where the original is vague.
- Preserve meaning, register, and length; this is a cleanup, not a rewrite from scratch. Keep technical content exactly as it was.
For a file: edit it in place and report the number and kinds of changes. For pasted text or a previous response: return the cleaned version, then a one-line summary of what was removed.
If ~/.claude/CLAUDE.md does not exist, say so and point to
https://github.com/aigorahub/stop-being-annoying-claude for the install.
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.
- 2mo ago First seen · 47 lines · 76 tokens per session scan A 210a4e6941fa
stop-the-charade is a skill published in the GitHub repository aigorahub/stop-being-annoying-claude (5 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 555 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 2026-08-31.
stop-the-charade compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stop-the-charadeaigorahub/stop-being-annoying-claude | Skill | 5 | 3mo ago | MIT | A | 76 | Claude Code, Codex |
| prompt-optimizationwecode-ai/Wegent | Skill | 885 | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| caliber-testingcaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| scoring-checkscaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 95 | Claude Code, Codex |
| writers-patterncaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 111 | Claude Code, Codex |
| llm-providercaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 100 | Claude Code, Codex |
| adding-a-commandcaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 76 | Claude Code, Codex |