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 design-honest-record-keepinggit 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/design-honest-record-keeping)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-honest-record-keeping"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-honest-record-keeping/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/design-honest-record-keeping"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-honest-record-keeping.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 | $0.00059 | $0.02939 |
| Opus 5 | $0.00030 | $0.01470 |
| Sonnet 5 | $0.00012 | $0.00588 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade A, and why
design-honest-record-keeping 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Honest Record Keeping
Establish institutional norms for recording events, decisions, and failures accurately and without euphemism — because organizations that record reality honestly develop better learning loops, earlier warning signals, and stronger accountability than those that soften unflattering facts.
Why This Is Best Practice
谷梁传 (Guliang Chi, ~5th–4th century BC) — Book of Commentary on the Spring and Autumn Annals:
Why best: The 谷梁传 is built around a single interpretive principle: the 春秋's value as a historical and moral record comes entirely from its accuracy. Each entry — how an event is named, what details are included, what is omitted — constitutes a permanent moral judgment. The text repeatedly analyzes cases where the 春秋 used a particular word or form to convey a moral assessment: calling a ruler's death "killed" rather than "died peacefully," recording a defeat accurately rather than calling it a "withdrawal." The 谷梁传's teaching: institutional records that use euphemism or omit unflattering facts corrupt not just the record but the institution's capacity for moral and operational judgment.
Google Site Reliability Engineering — Blameless Post-Mortems (Beyer et al., 2016): Google's SRE handbook establishes the blameless post-mortem as a foundational engineering practice. The key design requirement: "A postmortem that blames individuals is not a useful postmortem." The actual requirement is: record exactly what happened — what systems failed, what decisions were made, what the timeline was — without assigning individual blame, without softening technical failures, and without omitting decisions that contributed to the incident. Google's rationale: accurate records produce actionable learning; blame-focused or euphemized records produce self-protection. This practice is adopted at Netflix, Etsy, Atlassian, PagerDuty, and throughout the SRE community globally. The "blameless post-mortem" is now standard vocabulary in software reliability engineering.
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.
- 7d ago First seen · 78 lines · 59 tokens per session scan A 8468db0891d8
design-honest-record-keeping is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 59 tokens to every session and 2,939 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.
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.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
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.
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.