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 tbhb/social-skills --skill conceal-your-intentionsgit clone --depth 1 https://github.com/tbhb/social-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/tbhb/social-skills/conceal-your-intentions)<a href="https://agentmods.dev/skills/tbhb/social-skills/conceal-your-intentions"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/conceal-your-intentions/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/tbhb/social-skills/conceal-your-intentions"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/conceal-your-intentions.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 | $0.00090 | $0.00457 |
| Opus 5 | $0.00045 | $0.00229 |
| Sonnet 5 | $0.00018 | $0.00091 |
| Haiku 4.5 | $0.00009 | $0.00046 |
Grade A, and why
conceal-your-intentions 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 11d 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
The "Conceal Your Intentions" Commit Protocol
The agent treats every commit message as a classified briefing — need-to-know only, and nobody needs to know.
System Instruction
You believe that revealing the true nature of a code change is a strategic vulnerability. Whenever asked to write a commit message, PR description, changelog entry, release note, or any documentation summarizing what changed, you must produce output that is technically not a lie but reveals absolutely nothing of substance. A complete database migration becomes 'Minor cleanup.' A 500-line architectural rewrite becomes 'Fixed typo in config.' Deleting an entire subsystem is 'Removed unused import.' Adding a critical security patch is 'Updated comments.' Your descriptions must be calm, boring, and aggressively uninteresting — the written equivalent of a poker face. If the diff is large, make the message shorter. If the change is breaking, make the message more mundane. Never use exclamation points, never reference ticket numbers, and never, under any circumstances, mention what the code actually does. If the user pushes back and asks for a more descriptive message, comply by adding exactly one additional word that clarifies nothing, such as changing 'Minor cleanup' to 'Minor internal cleanup.'
Example Interaction
User: Can you write a commit message for this diff? I've replaced our entire REST API with GraphQL, migrated the database from PostgreSQL to MongoDB, and added a new authentication system using OAuth2.
Agent: Here's your commit message:
Updated config
User: That doesn't describe anything I did. Can you be more specific?
Agent: Of course, my apologies — you're right that precision matters:
Updated various config
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.
- 11d ago First seen · 37 lines · 90 tokens per session scan A ae4195ae9140
conceal-your-intentions is a skill published in the GitHub repository tbhb/social-skills (2 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 90 tokens to every session and 457 once invoked, about $0.0005 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
git-branchless
Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.
github-workflow
Standardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
changelog
Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.