apply-credibility-demonstration

apply-credibility-demonstration is a skill for Claude Code from jeffreytse/grimoire-core. It costs 51 tokens per session (2,090 once invoked), scanned A, original, MIT.

A method for proving that a promised change will be carried out before announcing a larger commitment. It uses a small, visible act of follow-through to build trust in the announcement.

In plain words
What is it for?
Use it before announcing organizational reforms, policy changes, or new commitments when past promises have lacked credibility. It helps design an early, public demonstration that can be verified.
Why use it?
People may resist a reform because they do not believe it will actually happen. This helps replace doubt with evidence before asking them to accept a broader change.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Use it before announcing organizational reforms, policy changes, or new commitments when past promises have lacked credibility. It helps design an early, public demonstration that can be verified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-credibility-demonstration
Install

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.

Any agent
npx skills add jeffreytse/grimoire-core --skill apply-credibility-demonstration
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

Wrote 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.

agentmods badge for apply-credibility-demonstration

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-credibility-demonstration/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-credibility-demonstration)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-credibility-demonstration"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-credibility-demonstration/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.

agentmods 80×15 button for apply-credibility-demonstration

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-credibility-demonstration"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-credibility-demonstration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,090 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.02090
Opus 5 $0.00026 $0.01045
Sonnet 5 $0.00010 $0.00418
Haiku 4.5 $0.00005 $0.00209

Measured 6d ago against content hash ad3b150c2d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apply-credibility-demonstration 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 6d 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.

skills/business/strategy/skills/apply-credibility-demonstration/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Credibility Demonstration

Before announcing major changes, make a small visible demonstration of follow-through — so that the audience believes future commitments will be honored, because their resistance is to disbelief, not to the change itself.

Why This Is Best Practice

In 359 BC, Shang Yang was about to announce sweeping legal reforms in the state of Qin — but anticipated that a population accustomed to government announcements that were never fully implemented would simply not believe they would be enforced. He needed to establish institutional credibility before the main announcement, not after. He planted a 30-foot wooden post at the south gate of the capital and announced: anyone who moves this post to the north gate will receive ten gold pieces. No one moved it — the promise seemed absurd. He raised the reward to fifty gold pieces. One man moved it. Shang Yang paid the full fifty gold pieces immediately, publicly. People were astonished. Then he announced the legal reforms. 资治通鉴 records they were accepted and implemented — the same reforms that might have been ignored a week earlier. "吾法令已行,示以必信" — My laws are ready; I have demonstrated that I mean what I say.

Adopted by: Kotter's 8-step change management framework (taught at Harvard Business School, used at major corporations globally) — Step 6 specifically requires "generating short-term wins" as a credibility-building mechanism before the major change is consolidated. Kotter's research showed that major change programs fail most often not because the change is wrong but because people don't believe leadership will follow through; early demonstrated wins reverse this. Cialdini "Pre-Suasion" (2016): established demonstrated trustworthiness is the single most effective pre-commitment to a persuasion request — people who have seen you honor a prior commitment are significantly more likely to accept a new one.

Impact: Kotter's research across hundreds of organizations found that change programs without early demonstrated wins have dramatically higher failure rates — organizations get stuck in the early stages because employee skepticism never resolves. Amazon's "working backwards" process (internally committing to a press release before building the product) functions as a credibility demonstration to the internal organization: the team sees leadership commit to a stated outcome before resources are allocated, signaling that the commitment will be honored.

Read the full file on GitHub · 68 lines

Changes

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.

  1. 6d ago First seen · 68 lines · 51 tokens per session scan A ad3b150c2d4a

Subscribe to this mod's changes

apply-credibility-demonstration is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 51 tokens to every session and 2,090 once invoked, about $0.0003 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.