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 agentmods add skills/deciqai/knowledge-skills/commitment-consistencynpx skills add deciqAI/knowledge-skills --skill commitment-consistencygit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWhat 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 | $0.00114 | $0.01800 |
| Opus 5 | $0.00057 | $0.00900 |
| Sonnet 5 | $0.00023 | $0.00360 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
commitment-consistency 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 3d 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.
Commitment and Consistency
Overview
Small commitments today dramatically raise the probability of large commitments tomorrow — people have a strong drive to behave consistently with prior choices, especially ones that were public, voluntary, and effortful. Freedman & Fraser (1966) showed a trivial petition tripled compliance with a much larger request two weeks later. Cialdini (1984) systematized it as one of six universal influence levers. Use this skill to design ethical commitment paths (onboarding, sales, hiring, fundraising) or to defend yourself when past commitments are pulling you toward choices you wouldn't otherwise make.
Composes with reciprocity, social-proof, anchoring, door-in-the-face, sunk-cost-fallacy.
When to Use
- Designing user onboarding, sales sequences, or commitment ladders
- Hiring or fundraising processes; behavior-change initiatives
- Evaluating whether past small steps are pulling you toward a current decision you wouldn't otherwise make
- Defending against high-pressure sales or escalation tactics
Not when: genuinely single-shot with no prior commitment history; framing would pressure someone with already limited choice.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete design or defense situation → run The Process directly.
- Coach mode: user is unfamiliar → 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.
- One-line: small commitments today substantially raise the probability of large commitments tomorrow — design ethically, and use the fresh-start question when defending.
- Check fit. No commitment history = design mode; prior commitments present = defense mode.
- Elicit the specific situation. What's the current decision or design? What prior commitments are relevant?
[WAIT — do not advance until user responds]
- One question at a time: what's the commitment ladder? Would I make this choice fresh? What's the ethical balance?
[WAIT — do not advance until user responds]
- Close: design or defense action + acknowledgment of the consistency drive + plan for re-evaluation.
[WAIT — do not advance until user responds]
What ships with it
3 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.
- 3d ago First seen · 122 lines · 114 tokens per session scan A a963dec66aee
commitment-consistency is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 17d ago), licensed MIT. It adds 114 tokens to every session and 1,800 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
judgment-training
当用户需要做方向性判断、评估「该往哪走/这事靠谱吗」、或想提升决策能力时调用。 核心理念: 判断力(知道行为长期后果)比努力重要; 清晰思考=从基础学科重建推理; 收集心智模型(复利/委托代理/可证伪性/基础数学)。 不适用于: 需要立即执行的具体任务步骤。 Triggers: 判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱/judgment/mental model/first principles.
shaman-musk
通玄真人·第一性原理 - 究万物之本，探第一性原理，化繁为简，质疑一切.
blindspot-check
Checks a big decision for blind spots against a catalogue of 95 cognitive biases before the user commits. Use when the user is about to make or has just justified a major life decision and wants to be checked for self-deception — buying a house, relocating, signing a long lease or contract, quitting or taking a job…
thinking-toolkit
A toolkit of 30 decision-making, problem-solving, systems-thinking, and communication models, plus a /logic mode that audits an argument's validity. This skill should be used when a user names a specific model, or describes a situation that calls for one: framing or reframing a problem, comparing options, setting…
cynefin-skill
Cynefin 框架（Cynefin Framework）的结构化意义建构工具。基于 Snowden、Kurtz、Boone 等一手来源的深度调研， 提炼 5 个核心原理和完整的操作协议。 触发词：「Cynefin」「cynefin」「问题分类」「5域框架」「复杂域」「繁杂域」。.
pareto-principle-skill
帕累托法则（80/20法则）的结构化思维工具。基于8个一手来源的深度调研， 提炼5个核心原理和完整的操作协议。 触发词：「帕累托」「80/20」「二八法则」「帕累托分布」「关键少数」「power law」「幂律」「长尾」。.