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 UKGovernmentBEIS/inspect_evals --skill write-an-adrgit clone --depth 1 https://github.com/UKGovernmentBEIS/inspect_evalsWrote 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/ukgovernmentbeis/inspect_evals/write-an-adr)<a href="https://agentmods.dev/skills/ukgovernmentbeis/inspect_evals/write-an-adr"><img src="https://agentmods.dev/badge/skills/ukgovernmentbeis/inspect_evals/write-an-adr/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/ukgovernmentbeis/inspect_evals/write-an-adr"><img src="https://agentmods.dev/badge/skills/ukgovernmentbeis/inspect_evals/write-an-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 49 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 51 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 53 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 55 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00038 | $0.01164 |
| Opus 5 | $0.00019 | $0.00582 |
| Sonnet 5 | $0.00008 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
write-an-adr 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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an Architectural Decision Record (ADR)
An ADR captures a single architecturally significant decision and its rationale. ADRs are stored in the adr/ directory at the repo root, numbered sequentially.
Background
This workflow follows the Nygard ADR format (Status, Context, Decision, Consequences) with practical additions (Date, Rationale, Considered Options) drawn from MADR and the project's existing conventions. See:
Prerequisites
- The user describes a decision that has been made (or is being proposed)
- If the user hasn't described the decision clearly, ask clarifying questions before writing
Steps
-
Determine the next ADR number:
- List files in
adr/and find the highest existing number - Increment by 1, zero-padded to 4 digits (e.g.,
0002)
- List files in
-
Gather information from the user:
- What problem or issue motivated this decision?
- What was decided?
- What alternatives were considered (if any)?
- What are the expected consequences (positive, negative, neutral)?
- What is the current status? (default:
Proposed) - If the user has already provided this information (e.g., in a design doc, PR discussion, or prior conversation), extract it rather than asking again
-
Write the ADR at
adr/NNNN-<slug>.mdusing the template below. The slug should be a short kebab-case summary of the decision (e.g.,use-huggingface-for-assets). -
Review with the user: Show them the file path and ask if they'd like any changes before considering it done.
Template
The ADR must use the structure in assets/adr-template.md. Copy that file as the starting point, then fill in the placeholders. All sections are required unless marked optional. Write in plain, direct language — avoid jargon and filler.
Placeholder guidance
| Placeholder | What to write |
|---|---|
{TITLE} |
A short noun phrase describing the decision (e.g., "Use HuggingFace Hub for Asset Hosting"). |
{STATUS} |
One of: Proposed, Accepted, Rejected, Deprecated, Superseded. Default to Proposed. If superseded, add a line: Superseded by [ADR-NNNN](NNNN-slug.md). If this supersedes another, add: Supersedes [ADR-NNNN](NNNN-slug.md). |
{DATE} |
YYYY-MM-DD — the date the decision was made or proposed. Use today's date unless the user specifies otherwise. |
{CONTEXT} |
The problem or situation motivating this decision. Describe forces at play — technical constraints, business requirements, team preferences, prior art. Reference issues, PRs, or prior ADRs. Should be understandable by someone unfamiliar with the history. |
{OPTION_A/B} |
If multiple approaches were evaluated, list them with pros/cons. Optional for straightforward decisions, recommended when the choice was non-obvious. |
{DECISION} |
The change being made. State clearly and concisely. Use active voice ("We will...", "Each eval will..."). Include enough detail to understand the change without reading the full implementation. |
| Consequences | Positive: what becomes easier, better, or more reliable. Negative: what becomes harder or more complex. Neutral (optional): side effects that are neither clearly positive nor negative. |
{RATIONALE} |
Optional. If the reasoning isn't fully captured by Context + Consequences, explain why this option was chosen. Especially useful when the decision is surprising or counterintuitive. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 76 lines · 38 tokens per session scan A 07998ec051d7
write-an-adr is a skill published in the GitHub repository UKGovernmentBEIS/inspect_evals (664 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,164 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…