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 agentmods add instructions/sbroenne/mcp-server-excel/development-workflowgit clone --depth 1 https://github.com/sbroenne/mcp-server-excelWhat 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 | $0.01518 | $0.01518 |
| Opus 5 | $0.00759 | $0.00759 |
| Sonnet 5 | $0.00304 | $0.00304 |
| Haiku 4.5 | $0.00152 | $0.00152 |
Grade A, and why
mcp-server-excel development-workflow.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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
Required process for all contributions
Branch Protection
⛔ NEVER commit directly to main
Enforced: PR reviews, CI/CD checks, create a branch first, up-to-date branches, no force pushes
Merge Strategy: Squash Merge
All PRs are merged using squash merge (single commit to main). This keeps git history clean and makes it easy to revert changes if needed. When you merge a PR:
- GitHub automatically squashes all commits from your branch into one commit
- Commit message is auto-populated from PR title/description — verify it's accurate before confirming merge
- Your feature branch can be safely deleted after merge
Development Process
- Create feature branch:
git checkout -b feature/name - Standards: Zero warnings, targeted tests pass, docs updated, security rules followed
- PR Checklist: Build passes, applicable tests pass, docs updated, patterns followed, changeset added when user-visible
- Check PR review comments: After creating PR, retrieve automated review feedback and fix all verified issues
- Versions: Automated via release workflow - don't update manually
PR Review Comment Workflow
After creating a PR, ALWAYS check for automated review comments:
# Retrieve inline code review comments using GitHub CLI
# ⚠️ IMPORTANT: for this public repo, gh CLI must be authenticated as a PERSONAL GitHub account.
# Enterprise Managed User (EMU) accounts cannot access public repos via gh CLI.
# Verify with: gh auth status
# If needed, select the personal account's token (Copilot CLI exposes it as an env var):
# $env:GH_TOKEN = $env:COPILOT_GH_ACCOUNT_github_2E_com_sbroenne # then verify: gh api user --jq '.login'
# (Admin ops — rulesets, disabling workflows, deleting runs — require this personal token, not the EMU account.)
gh api repos/sbroenne/mcp-server-excel/pulls/PULL_NUMBER/comments --paginate
Common automated reviewers:
- Copilot (code quality, performance, style)
- github-advanced-security (security scanning, code analysis)
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.
- yesterday First seen · 138 lines · 1,518 tokens per session scan A 9d80a45ca5fc
mcp-server-excel development-workflow.instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-server-excel (645 stars, last pushed 2d ago), licensed MIT. It adds 1,518 tokens to every session, about $0.0076 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 instructions, from other repositories
mcp-server-powerpoint copilot-instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering project instructions — powerpointmcp, critical files (read these first), sister projects, what is powerpointmcp? and session model (mcp server).
mcp-server-powerpoint architecture-patterns.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).
mcp-server-powerpoint critical-rules.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering critical rules - must follow, rule 1: success/errormessage invariant, rule 1b: no exception suppression in core, rule 30: real-com integration tests only, strict tdd and rule: 1-based indexing everywhere.
mcp-server-powerpoint mcp-server-guide.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering mcp server development guide, llm-facing content rules, two kinds of tools: hand-written vs. generated, implementation pattern: single hand-written dispatch tool and error handling (mandatory).
mcp-server-powerpoint testing-strategy.instructions.md
Instructions for sbroenne/mcp-server-powerpoint, covering testing strategy, strict tdd (red → green), test project layout, serialization is mandatory and trait tagging (required for surgical filtering).
mcp-wireshark CLAUDE.md
Instructions for khuynh22/mcp-wireshark, covering claude.md — mcp-wireshark, purpose, architecture, code conventions and token efficiency rules.