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-honor-prior-commitmentgit 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-honor-prior-commitment)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-honor-prior-commitment"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-honor-prior-commitment/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-honor-prior-commitment"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-honor-prior-commitment.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 | $0.00077 | $0.03978 |
| Opus 5.5 | $0.00031 | $0.01591 |
| Sonnet 5.5 | $0.00015 | $0.00796 |
| Haiku 4.5 | $0.00008 | $0.00398 |
Grade A, and why
apply-honor-prior-commitment 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 4d 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 Honor Prior Commitment
When a prior public commitment has become tactically costly to honour, honour it visibly and completely — because the strategic asset created by demonstrated trustworthiness under cost exceeds the value of the short-term gain from breaking the commitment, and because the reputation for keeping commitments under cost is the only reliable signal of genuine trustworthiness, since commitments that are only kept when convenient prove nothing.
Why This Is Best Practice
Origin: In 636 BC, Chong'er (重耳), the exiled prince of Jin, was being sheltered by the King of Chu during his nineteen years of wandering before reclaiming the Jin throne. The King of Chu asked Chong'er: if you ever become ruler of Jin and our two states come into conflict, what will you do? Chong'er replied: "I will order our troops to retreat three days' march (退避三舍, approximately 90 li) out of respect for your kindness today." The King of Chu's advisor urged the king to kill Chong'er immediately — a future ruler of Jin making no such concession was dangerous. The king declined and let Chong'er go.
In 632 BC, Chong'er had become Duke Wen of Jin (晋文公). The Jin and Chu forces met in what would become the Battle of Chengpu (城濮之战). True to his promise of sixteen years earlier, Duke Wen ordered his forces to retreat three days' march. His own commanders objected: they were strong, the retreat was unnecessary, and retreating before battle would signal weakness to both Chu and their own troops. Duke Wen's response was precise: I made this promise when Chu's king showed me kindness; I am not retreating out of military calculation but out of moral obligation. The retreat happened.
The outcome was unexpected in every way that his commanders had feared it would not be: the three-day retreat gave Duke Wen's forces a defensive position they could choose, gave time for Chu's commanders to become overconfident, and — critically — gave Duke Wen's own troops a moral narrative that was galvanising. Duke Wen's forces did not feel they were losing when they retreated; they felt they were watching their leader demonstrate an integrity so complete that it held under military pressure. When the battle finally came at Chengpu, Jin won decisively, and Duke Wen's moral authority — already established by the retreat — made the victory a foundation for Jin's subsequent hegemony in the central plains.
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.
- 4d ago First seen · 122 lines · 77 tokens per session scan A f1fc0a1fd898
apply-honor-prior-commitment is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 3,978 once invoked, about $0.0003 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 2026-10-17.
Other skills, from other repositories
long-term-compounding
A decision guide based on the idea that wealth, knowledge, trust, relationships, and reputation can grow through repeated long-term choices. It favors lasting, mutually beneficial partnerships over short-term gains.
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.
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.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.