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 Bono12138/bonobox --skill reality-strategygit clone --depth 1 https://github.com/Bono12138/bonoboxWrote 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/bono12138/bonobox/reality-strategy)<a href="https://agentmods.dev/skills/bono12138/bonobox/reality-strategy"><img src="https://agentmods.dev/badge/skills/bono12138/bonobox/reality-strategy/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/bono12138/bonobox/reality-strategy"><img src="https://agentmods.dev/badge/skills/bono12138/bonobox/reality-strategy.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 | $0.00116 | $0.04640 |
| Opus 5.5 | $0.00046 | $0.01856 |
| Sonnet 5.5 | $0.00023 | $0.00928 |
| Haiku 4.5 | $0.00012 | $0.00464 |
Grade A, and why
reality-strategy 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
丢掉幻想,准备斗争
Help the user change the situation, not merely understand or describe it.
Capability version: 1.2.0.
Own one continuous loop:
- separate what people say from what actually keeps the situation in place;
- investigate the real decision chain and distinguish between competing explanations;
- map the people, interests, costs, permissions and quiet vetoes around one result;
- design a move aimed at the confirmed obstacle;
- observe the response, preserve what was gained and choose the next move.
Use $reality-grounding internally when decision-changing facts are missing. Read references/stakeholder-map.md when several people can affect the result. Read references/power-shifting-moves.md before solving a blocked organisational, repeated-chasing, credit, permission or coordination case. Read references/political-strategy-patterns.md when status, face, informal influence or counter-moves matter. Read references/evaluation-cases.md when modifying or testing this Skill.
Do not ask the user to select an internal stage or read the framework.
Do not complete the scene for the user
Use only facts stated by the user or found in approved evidence. Do not add a plausible colleague, manager, customer need, policy, approval route, supplier, system feature, meeting, deadline, permission or past event to make a strategy work.
Before choosing a move, separate the scene privately into:
- given: stated or observed facts that may be used directly;
- unknown: facts that would change the move and must be asked or checked;
- hypothesis: possible explanations that may guide a question but may not be written as what happened.
A recommendation may tell the user to create something new or check whether a route exists. It may not describe that object or route as already available. For example, “ask finance whether there is a late-approval route” is valid when no route is known; “use the finance exception route” invents a fact.
Audit every material person, rule, permission, process and consequence in the proposed action. If its source is neither the user's account nor inspected evidence, convert it into a question or a conditional branch. When that unknown determines the first move, ask and stop. Plausibility is not evidence, and a useful-sounding invented detail is still a failure.
What ships with it
7 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.
- 2mo ago First seen · 321 lines · 116 tokens per session scan A 7d544bb58970
reality-strategy is a skill published in the GitHub repository Bono12138/bonobox (6 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 4,640 once invoked, about $0.0005 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 2026-09-05.
reality-strategy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reality-strategyBono12138/bonobox | Skill | 6 | 1mo ago | MIT | A | 116 | Codex |
| @elad12390/web-research-assistantelad12390/web-research-assistant | Skill | 9 | 10d ago | MIT | A | 150 | Claude Code, Codex |
| mcp-tool-developerLiHongwei-cn/lihongwei-cn | Skill | 5 | 29d ago | MIT | A | 38 | Claude Code, Codex |
| click-to-mcpCoding-Dev-Tools/click-to-mcp | Skill | 8 | 1mo ago | none | A | 104 | Claude Code |
| open-sourcebrowser-use/browser-use | Skill | 120k | today | MIT | A | 137 | Claude Code |
| design-mcp-servercyanheads/obsidian-mcp-server | Skill | 702 | 7d ago | Apache-2.0 | A | 62 | Claude Code |
| api-canvascyanheads/obsidian-mcp-server | Skill | 702 | 7d ago | Apache-2.0 | A | 85 | Claude Code |