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 deciqAI/knowledge-skills --skill change-and-constantsgit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/change-and-constants)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/change-and-constants"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/change-and-constants/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/deciqai/knowledge-skills/change-and-constants"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/change-and-constants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.01909 |
| Opus 5 | $0.00056 | $0.00955 |
| Sonnet 5 | $0.00022 | $0.00382 |
| Haiku 4.5 | $0.00011 | $0.00191 |
Grade A, and why
change-and-constants 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change and Constants Framework
Overview
Every strategy contains elements that must change and elements that must not. The failure mode is misclassification: treating habits as principles, or principles as outdated conventions. The framework sorts on two axes: 变 (Must Change) and 不变 (Must Stay Constant) — they are complements, not opposites.
Skill composition: AFTER [first-principles] to strip convention; WITH [second-order-thinking] to check if "constants" are only temporarily stable; BEFORE [okr-goal-setting] — goals = 变; core values = 不变.
When to Use
- Major environmental shift demands strategic response and the team is paralyzed on what to adapt vs. preserve
- Organizational identity is unclear: cannot distinguish "this is who we are" from "this is what we've always done"
- Leader/board asks: "What should we never compromise on?" or "Is this signal or noise?"
- Retrospective after failure: distinguish bad implementation of a sound constant vs. faithful adherence to an outdated variable
When NOT to use: purely operational decisions (vendor, tool) without strategic identity implications; genuine emergencies (use OODA instead); using the framework to avoid deciding by treating all elements as equivalent.
Coaching Novices (Adaptive Front Door)
- Engine mode: concrete case → run The Process directly.
- Coach mode: unfamiliar user → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- What-it-is: "变/不变 sorts everything in your strategy into 'must adapt' or 'must preserve' using two explicit tests, not intuition."
- Check fit: "Is there a situation where you're unclear whether to change something — caught between adapting and staying true to who you are?"
- Elicit their case: "What are you navigating? Which things feel like they might need to change, and which should never change?"
[WAIT — do not advance until user responds]
- Run The Process step by step with their input — list elements first, then Test A, then Test B.
[WAIT — do not advance until user responds]
- Close by naming which things they had been treating as constants that are actually habits.
[WAIT — do not advance until user responds]
What ships with it
2 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.
- 11d ago First seen · 123 lines · 111 tokens per session scan A 647bf7e0f133
change-and-constants is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 111 tokens to every session and 1,909 once invoked, about $0.0006 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
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
ai-seo
Optimizes content to get cited by AI assistants (ChatGPT, Perplexity, Google AI Overviews) and rank in classic SERPs — entity-rich intros, question-shaped H2s, 40-60 word extractable answers, schema.org JSON-LD, llms.txt, internal links, and E-E-A-T signals. Runs in audit or rewrite mode. Use when the user says…