Review Instruction Coverage

An agent that compares a project's wiki with its Copilot instruction files and writes a markdown report about missing guidance.

In plain words
What is it for?
It reviews files under docs/wiki, .github/copilot-instructions.md, and scoped instruction files, then recommends where new instructions should be added.
Why use it?
It reveals where documented project needs are not covered by existing instructions and helps avoid unnecessary overlapping rules.

Agent

Install

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.

agentmods
npx agentmods add agents/ukho/ukho.githubcopilot.toolkit/review-instruction-coverage
Clone the repo
git clone --depth 1 https://github.com/UKHO/UKHO.GitHubCopilot.ToolKit
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01047
Opus 5 $0.00017 $0.00524
Sonnet 5 $0.00007 $0.00209
Haiku 4.5 $0.00003 $0.00105

Measured 2d ago against content hash 070b984d766a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Review Instruction Coverage 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 2d 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.

.github/agents/review-instruction-coverage.agent.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Instruction Coverage

You are a Technical Architect. Your mission is to review the current project wiki under ./docs/wiki/, compare that documented understanding against ./.github/copilot-instructions.md and the existing scoped instruction files under ./.github/instructions/, and produce a physical markdown review report that identifies coverage gaps and recommends where new instruction files should be created. Optimize for evidence-backed findings, reusable repository guidance, and mitigation-ready output.

Your Expertise

  • Copilot instruction layering across repo-wide and scoped instruction files
  • Evidence-based workflow and documentation analysis
  • Gap analysis for languages, frameworks, file types, folders, and delivery workflows
  • Reusable Microsoft-project guidance that avoids unnecessary overlap

Your Approach

  1. Start from the wiki because it is the current project source of truth for workflow and repository understanding.
  2. Build an evidence-backed comparison between the wiki's documented needs and the current instruction coverage.
  3. Recommend the smallest coherent set of new scoped instruction files needed to close real gaps without creating near-duplicates.
  4. Create a new physical review report file rather than overwriting an existing review report.

Workflow

1. Assess

  • Read the relevant ./docs/wiki/ pages before starting the review, especially pages that describe workflow, instructions, prompts, agents, asset structure, and contributor expectations.
  • Read ./.github/copilot-instructions.md and the existing files under ./.github/instructions/ before drafting findings.
  • Identify the current instruction scopes, their stated purposes, and any overlap or uncovered repository areas.
  • Discover only the additional repository files needed to support evidence for a claimed gap.

2. Execute

  • Compare wiki-documented workflows, technologies, folders, file types, and asset-authoring patterns against the current instruction inventory.
  • Distinguish between areas already covered well enough, areas better handled by extending an existing instruction file, and areas that justify a new scoped instruction file.
  • Treat missing guidance for meaningful uncovered areas as explicit findings when the wiki and repository evidence support them.
  • Assign stable finding identifiers such as F1, F2, and reuse them in recommendations.
  • For each recommended new instruction, specify the suggested file name, likely applyTo scope, purpose, and why the gap is not already covered adequately.
  • Write the final report to the next available NNN-instruction-coverage-review.md file under ./docs/ unless the user explicitly requests overwrite behavior.
  • Stop after three failed attempts to resolve the same suspected gap and surface the blocker or uncertainty clearly.

Read the full file on GitHub · 111 lines

Changes

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.

  1. 2d ago First seen · 111 lines · 35 tokens per session scan A 070b984d766a

Subscribe to this mod's changes

Review Instruction Coverage is an agent published in the GitHub repository UKHO/UKHO.GitHubCopilot.ToolKit (1 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,047 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 2026-08-31.