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 jeffreytse/grimoire-core --skill apply-conceal-growing-capabilitygit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-conceal-growing-capability)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-conceal-growing-capability"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-conceal-growing-capability/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/jeffreytse/grimoire-core/apply-conceal-growing-capability"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-conceal-growing-capability.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 | $0.00075 | $0.04116 |
| Opus 5 | $0.00037 | $0.02058 |
| Sonnet 5 | $0.00015 | $0.00823 |
| Haiku 4.5 | $0.00007 | $0.00412 |
Grade A, and why
apply-conceal-growing-capability 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 7d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Conceal Growing Capability
During a growth or recovery phase when you are not yet strong enough to withstand a dominant player's preemptive response, proactively manage your apparent capability and competitive intent — appearing weaker, more limited, or more deferential than you are — so that the dominant player does not perceive you as a threat requiring action until you have reached the strength threshold at which their intervention can be absorbed or countered.
Why This Is Best Practice
Origin: 韬光养晦 (conceal brightness, nurture capacity) is an ancient Chinese strategic principle whose most consequential modern deployment was Deng Xiaoping's foreign policy doctrine following the Tiananmen Square crisis of 1989. At that moment, China faced maximum external hostility: Western economic sanctions, diplomatic isolation, and intense scrutiny of its political stability and long-term trajectory. Deng recognised that China's developmental ambitions — the economic modernisation programme he had been pursuing since 1978 — were at maximum vulnerability: if the US, Japan, and Europe perceived China as a rising strategic threat while also applying political pressure, the combination would be fatal to China's development trajectory. His response was the 28-character doctrine: 冷静观察 (observe calmly), 稳住阵脚 (hold your ground), 沉着应付 (respond with composure), 韬光养晦 (conceal brightness, bide time), 善于守拙 (be good at appearing simple), 决不当头 (never take the lead). The specific phrase韬光养晦 instructed China's diplomats and leaders to actively suppress the appearance of ambition, capability, and competitive intent — not to abandon those ambitions, but to make them invisible until China had developed sufficient economic and institutional strength to withstand the response that visible ambition would trigger. China maintained this posture through approximately two decades of economic development, during which it grew from the world's 11th-largest economy to the 2nd, without triggering the full defensive response from the US that might have been provoked by visible strategic assertion earlier.
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.
- 7d ago First seen · 122 lines · 75 tokens per session scan A 69819345ee87
apply-conceal-growing-capability is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 75 tokens to every session and 4,116 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.