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-fidelity-before-adaptationgit 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-fidelity-before-adaptation)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-fidelity-before-adaptation"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-fidelity-before-adaptation/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-fidelity-before-adaptation"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-fidelity-before-adaptation.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 | $0.00081 | $0.01852 |
| Opus 5.5 | $0.00032 | $0.00741 |
| Sonnet 5.5 | $0.00016 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
apply-fidelity-before-adaptation 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 Fidelity Before Adaptation
When adopting a new external process, methodology, or evidence-based practice, implement it with strict fidelity to its original design first — resisting customization based on discomfort or habit — because premature adaptation by people who don't yet understand why the original design works is a well-documented cause of the practice failing to reproduce its intended effectiveness; only begin deliberate optimization once faithful execution has actually been demonstrated.
Why This Is Best Practice
Why best: A newly adopted process was designed the way it is for reasons the adopting organization typically does not yet fully understand — the parts that feel most uncomfortable or unfamiliar are often exactly the elements that differ most from the organization's prior (less effective) habits, and therefore exactly the elements it most needs. Allowing customization before the organization has actually executed the process faithfully means changes get made based on discomfort and pre-existing habit rather than on any real evidence about what does or doesn't work — and this specific failure mode, adapting before achieving fidelity, is what implementation research identifies as a primary reason imported practices fail to reproduce the results they were adopted to achieve.
Fixsen, Naoom, Blase, Friedman & Wallace (2005): This synthesis of implementation research, produced by the National Implementation Research Network, formalized a staged model of how evidence-based practices succeed or fail when adopted by a new organization — Exploration, Installation, Initial Implementation, Full Implementation, and Innovation — and specifically identified premature local adaptation, occurring before an organization has established fidelity to the practice's original design, as a recurring, well-documented cause of adopted practices failing to reproduce the effectiveness they demonstrated in their original context. The framework explicitly distinguishes adaptation informed by evidence gathered during faithful execution (legitimate, and expected in the later "Innovation" stage) from adaptation driven by discomfort or habit before fidelity has been achieved (a documented failure mode).
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 · 81 tokens per session scan A 140a35c88eef
apply-fidelity-before-adaptation is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,852 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.