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-narrative-memo-disciplinegit 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-narrative-memo-discipline)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-narrative-memo-discipline"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-narrative-memo-discipline/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-narrative-memo-discipline"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-narrative-memo-discipline.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 | $0.00078 | $0.02058 |
| Opus 5.5 | $0.00031 | $0.00823 |
| Sonnet 5.5 | $0.00016 | $0.00412 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
apply-narrative-memo-discipline 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Narrative Memo Discipline
Require a structured, full-sentence written narrative for any significant decision instead of a slide presentation, and have the room read it silently before discussion begins — because bullet-point slide formats systematically let weak analysis, unsupported claims, and missing logical connections pass unchallenged in a way that full-sentence prose does not.
Why This Is Best Practice
Why best: A bullet-point slide format does not require the author to state the actual logical relationship between claims — bullets can be juxtaposed on a slide without ever specifying whether one causes another, contradicts another, or is merely adjacent to it, and a fluent presenter can paper over that missing logic with delivery. A full-sentence narrative document cannot hide this gap: a claim has to be stated as a complete sentence with an explicit logical connector to the next one, which forces the author to either supply the actual reasoning or expose its absence on the page, where a reader can catch it before a decision is made rather than after.
Tufte, "The Cognitive Style of PowerPoint" (2003): Tufte's analysis specifically examined a PowerPoint slide used in NASA communications during the 2003 Space Shuttle Columbia mission, which presented data about a foam-strike risk to the shuttle's wing in a nested hierarchy of terse bullet points. The Columbia Accident Investigation Board's own subsequent report concluded that the slide's format compressed and obscured the severity of the underlying engineering data to the point that key decision-makers did not grasp the actual risk being described — a documented, high-stakes, real-world case in which the compression inherent to bullet-point slide format contributed to a fatal misjudgment, not merely a stylistic complaint about slides being unaesthetic.
Jeff Bezos, Amazon 2017 Shareholder Letter: Bezos describes Amazon's standard practice for important decision-making meetings: instead of a slide presentation, the meeting's presenter writes a structured, full-sentence narrative memo (Amazon's convention caps it at six pages), and the meeting begins with everyone silently reading the memo in the room ("study hall") before any discussion starts. Bezos explains the rationale directly: a good memo forces better thought and better understanding of what's actually important versus what's not, in a way that a slide presentation's structure inherently does not — because the act of writing complete sentences and paragraphs requires the author to actually work out the argument, not merely gesture at it.
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.
- 1mo ago First seen · 65 lines · 78 tokens per session scan A 86aa1d6dfab8
apply-narrative-memo-discipline is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 2,058 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 2026-09-03.
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.
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.
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.