Use it in orchestrated coding workflows to record failed reviews, repeated steps, validation errors, deployment-policy issues, and user-raised concerns.

Important process problems can be forgotten after a workflow finishes. This preserves what went wrong so future runs can improve.

How jonathan-vella/apex-accelerator configures GitHub Copilot

Q: What is apex-accelerator lesson-collection.instructions.md?

A process for recording observations and lessons from workflow runs. It creates lessons-learned files when reviews fail, revisions are needed, validation breaks, or other defined problems occur.

Reuse

Borrowing it

Nothing to install: this file belongs to jonathan-vella/apex-accelerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jonathan-vella/apex-accelerator/main/.github/instructions/lesson-collection.instructions.md

Clone the repo

git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/lesson-collection.svg)](https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/lesson-collection)

Your own site

<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/lesson-collection"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/lesson-collection.svg" alt="Measured on agentmods" height="20"></a>

Per session 568 This file is loaded in full into every session.

When invoked 568 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00568	$0.00568
Opus 5	$0.00284	$0.00284
Sonnet 5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 7d ago against content hash 74454ff36e2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

apex-accelerator lesson-collection.instructions.md 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.

.github/instructions/lesson-collection.instructions.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lesson Collection Protocol

Orchestrators collect process observations during workflow execution and generate 09-lessons-learned.json + 09-lessons-learned.md as workflow completion artifacts (same pattern as 00-handoff.md and 00-session-state.json).

Initialization

At workflow start (when creating 00-session-state.json), also create:

// agent-output/{project}/09-lessons-learned.json
{
  "workflow_mode": "production",
  "project": "{project}",
  "lessons": []
}

Set workflow_mode to "e2e" for the E2E Orchestrator.

When to Record a Lesson

Production Orchestrator Triggers

Challenger review returns must_fix findings
User rejects an artifact and requests revision (log what was wrong)
Subagent returns NEEDS_REVISION verdict
Deployment what-if reveals Azure Policy violations
User explicitly flags an issue or concern during approval

E2E Orchestrator Triggers (superset of production)

All production triggers PLUS:

Step needs >1 iteration (self-correction fired)
Validator fails on first pass
Pre-validation fails (agent returned empty/garbage)
bicep build or terraform validate fails with hallucinated properties → category factual-accuracy
Step exceeds timing threshold → category workflow-design

Lesson Schema

Formal JSON Schema: tools/schemas/lesson-log.schema.json. Required fields per entry: id, step, category, severity, title, observation, root_cause, recommendation, applies_to, applies_to_paths, status.

Completion Protocol

After the final workflow step completes (Step 7 for production, Phase H for E2E), generate the lessons-learned artifacts:

Read 09-lessons-learned.json — the accumulated lesson entries
Generate 09-lessons-learned.md narrative using the H2 structure from azure-artifacts/templates/09-lessons-learned.template.md
If zero lessons were captured, write a "clean run" summary: all steps passed without revision, no challenger must_fix findings
Update 00-session-state.json — add 09-lessons-learned.json and 09-lessons-learned.md to the artifacts list

Read the full file on GitHub · 67 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.

7d ago First seen · 67 lines · 568 tokens per session scan A 74454ff36e2a

Subscribe to this mod's changes

apex-accelerator lesson-collection.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 5d ago), licensed MIT. It adds 568 tokens to every session, about $0.0028 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.

Building agents Planning agentic-ai azure bicep copilot github-copilot iac

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

apex-accelerator: Instructions file for GitHub Copilot