What is specrew copilot-instructions.md?

A repository instruction file describing Specrew's technologies, project layout, commands, coding rules, and stored review evidence.

It helps agents work on Specrew code and its Markdown, YAML, JSON, and PowerShell files.

It gives coding agents consistent guidance about how this project is organised and maintained.

How alonf/specrew configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to alonf/specrew. 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/alonf/specrew/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/alonf/specrew

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/alonf/specrew/copilot-instructions.svg)](https://agentmods.dev/instructions/alonf/specrew/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/alonf/specrew/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/alonf/specrew/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,163 This file is loaded in full into every session.

When invoked 3,163 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03163	$0.03163
Opus 5	$0.01581	$0.01581
Sonnet 5	$0.00633	$0.00633
Haiku 4.5	$0.00316	$0.00316

Measured 2d ago against content hash 338cdc72495b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

specrew copilot-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 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/copilot-instructions.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specrew Development Guidelines

Auto-generated from all feature plans. Last updated: 2026-06-17

Active Technologies

PowerShell 7.x plus Markdown/YAML/JSON governance and contract artifacts. + Existing Specrew module/script surfaces, Git CLI, and installed headless AI host CLIs when explicitly configured/authorized; no new dependencies. (197-continuous-co-review)
Versioned filesystem artifacts only. Durable evidence under .specrew/review/inline/<run-id>/...; temporary immutable bundles in per-run workspaces. (197-continuous-co-review)
PowerShell 7.x plus Markdown/YAML/JSON governance artifacts + scripts/specrew.ps1, scripts/specrew-update.ps1, scripts/specrew-start.ps1, Specrew.psd1, extensions/specrew-speckit/scripts/validate-governance.ps1, mirrored .specify/extensions/specrew-speckit/scripts/validate-governance.ps1, tests/integration/publish-module-harness.tests.ps1, tests/integration/non-specrew-session-bypass.tests.ps1, and the Spec Kit prompt/workflow surfaces for /speckit.specify (049-pipeline-hardening-intake)
Git-tracked Markdown/YAML/JSON/PowerShell assets under docs/, scripts/, extensions/, .specify/, .github/, and specs/049-pipeline-hardening-intake/ (049-pipeline-hardening-intake)
PowerShell 7.x scripts plus Markdown/YAML/JSON governance artifacts; downstream Specrew config currently pins Spec Kit 0.12.9 and Squad 0.11.0 in .specrew/config.yml + extensions/specrew-speckit script/template surfaces, .specify plan workflow, Squad-native runtime deployment via deploy-squad-runtime.ps1, existing governance/evaluation scripts under tests/integration/ and tests/support/ (008-quality-profile-foundation)
Git-tracked Markdown/YAML assets under .specrew/ plus feature and iteration artifacts under specs/<feature>/; machine-readable mechanical findings stored as JSON sidecars (008-quality-profile-foundation)
PowerShell 7.x scripts plus Markdown/YAML/JSON governance artifacts; downstream Specrew config remains rooted in .specrew/*.yml + extensions/specrew-speckit scripts/templates, .specify planning workflow, existing Phase 1 quality-profile/evidence contracts, iteration governance scripts, and deterministic integration coverage in tests/integration/ (008-quality-profile-foundation)
Git-tracked Markdown/YAML/JSON under .specrew/, extensions/specrew-speckit/templates/quality/, and specs/<feature>/iterations/<NNN>/quality/; Phase 2 adds a versioned known-traps corpus plus hardening/lens evidence artifacts (008-quality-profile-foundation)
PowerShell 7.x plus Markdown/YAML/JSON governance artifacts + extensions/specrew-speckit governance scripts/templates, .specify planning workflow, feature-local planning artifacts, and deterministic integration tests under tests/integration/ (008-quality-profile-foundation)
Git-tracked Markdown/YAML/JSON in specs/005-stack-aware-quality-bar/, .specify/, .specrew/, and extensions/specrew-speckit/ (008-quality-profile-foundation)
PowerShell 7.x plus Markdown/YAML/JSON governance artifacts + extensions/specrew-speckit governance scripts (manage-escalation-state.ps1, shared-governance.ps1, sync-squad-model-overrides.ps1, validate-governance.ps1), .specrew runtime config, .squad routing/ledger artifacts, and feature-local spec artifacts (008-reviewer-escalation-symmetry)
Git-tracked Markdown/YAML/JSON in specs/008-reviewer-escalation-symmetry/, .specrew/, .squad/, .github/agents/, and extensions/specrew-speckit/ (008-reviewer-escalation-symmetry)
PowerShell 7+ (pwsh) for the bootstrap banner function; Markdown (CommonMark) for documentation files + None — plain Markdown + existing PowerShell function; no new packages or tooling (010-onboarding-resume-visibility)
File system only — four existing files in the Specrew repository (010-onboarding-resume-visibility)
PowerShell 7.x automation plus Markdown/YAML/JSON governance artifacts + Existing Specrew Spec Kit extension surfaces, Squad/Copilot startup guidance, PowerShell validator/test scripts, Markdown contracts and checklists (012-keep-descriptive-refs)
Git-tracked repository files only (.md, .ps1, .yml, .json); no database changes (012-keep-descriptive-refs)
PowerShell 7.x + extensions/specrew-speckit/scripts/validate-governance.ps1, shared-governance.ps1, scripts/specrew-start.ps1; Git working-tree inspection via git status --porcelain (013-validator-hardening)
Git-tracked Markdown governance artifacts (specs/*/iterations/*/state.md, quality/hardening-gate.md, plan.md, review.md, retro.md, .github/copilot-instructions.md, .specrew/quality/known-traps.md) (013-validator-hardening)
PowerShell 7.x automation plus Markdown/YAML/JSON governance artifacts + extensions/specrew-speckit/validators/handoff-governance-validator.ps1, coordinator prompt/checklist surfaces under extensions/specrew-speckit/, specs/001-specrew-product/contracts/coordinator-handoff-template.md, .github/agents/squad.agent.md, .squad/templates/squad.agent.md, .specrew/quality/known-traps.md, existing integration tests under tests/integration/ (014-handoff-format-scoping)
Git-tracked repository artifacts only (.md, .ps1, .json, .yml); no database or external state changes (014-handoff-format-scoping)
PowerShell 7 (script extension), Markdown (all documentation artifacts), Git (tag operations) + validate-governance.ps1 and shared-governance.ps1 (existing); standard (015-public-readiness-pass)
Filesystem only — Markdown files at repo root and under docs/, specs/, and extensions/specrew-speckit/ (015-public-readiness-pass)
PowerShell 7 for validator/test automation, Markdown for prompt/contracts/docs, Git commit metadata for boundary-signature inspection + extensions/specrew-speckit/scripts/validate-governance.ps1; extensions/specrew-speckit/scripts/shared-governance.ps1; extensions/specrew-speckit/validators/handoff-governance-validator.ps1; coordinator prompt surfaces under extensions/specrew-speckit/prompts/ and .github/agents/ (016-substantive-interaction-model)
Filesystem + Git history + .squad/decisions.md authorization ledger + .specrew/quality/known-traps.md corpus (016-substantive-interaction-model)
PowerShell 7.x scripts plus Markdown/YAML/JSON governance artifacts + scripts/specrew.ps1, scripts/specrew-where.ps1, mirrored extensions/specrew-speckit + .specify/extensions/specrew-speckit governance scripts, .specify/feature.json, .specrew/iteration-config.yml, .specrew/role-assignments.yml, specs/** iteration artifacts, .specrew/roadmap.yml, and Git-tracked docs/tests (017-velocity-dashboard)
PowerShell 7.x scripts plus Markdown/YAML/JSON governance artifacts + scripts/internal/dashboard-renderer.ps1, scripts/specrew.ps1, (018-velocity-dashboard-visual-richness)
Git-tracked file artifacts only under specs/, .specrew/, .specify/, docs/, (018-velocity-dashboard-visual-richness)
PowerShell 7.x scripts plus Markdown/YAML/JSON governance artifacts + scripts/internal/dashboard-renderer.ps1, scripts/specrew.ps1, scripts/specrew-where.ps1, mirrored extensions/specrew-speckit + .specify/extensions/specrew-speckit closeout/validator scripts, .specify/feature.json, .specrew/roadmap.yml, specs/** dashboard artifacts, docs/dashboard-guide.md, README.md, and dashboard fixture/test harnesses under tests/ (018-velocity-dashboard-visual-richness)
Git-tracked file artifacts only under specs/, .specrew/, .specify/, docs/, scripts/, extensions/, and tests/ (018-velocity-dashboard-visual-richness)
PowerShell 7+ for runtime scripts and module entry points; Markdown/YAML skill metadata for the slash-command contract + Existing scripts/specrew.ps1 dispatcher, Specrew.psm1 alias/module surface, Specrew distribution/update flows, Squad-native SKILL.md deployment surfaces, shared governance/version-check helpers (021-specrew-slash-commands)
File-based only: legacy .copilot/skills/ migration targets plus .squad/templates/skills/, .specrew/config.yml, feature docs under specs/021-specrew-slash-commands/, and existing repository scripts/docs (021-specrew-slash-commands)
PowerShell 7.x for the active runtime/test lane, while preserving existing Specrew PowerShell module compatibility expectations + scripts/specrew-start.ps1, scripts/internal/sync-boundary-state.ps1, extensions/specrew-speckit/scripts/scaffold-feature-closeout-dashboard.ps1, lifecycle sync command wrappers under extensions/specrew-speckit/commands/, shared governance helpers, Git CLI (022-hotfix-schema-tests)
File-based only (.specrew/, .squad/, specs/, tests/) (022-hotfix-schema-tests)
PowerShell 7.0+ (per Specrew.psd1 PowerShellVersion requirement) + PowerShell-Yaml module (for YAML parsing), ConvertFrom-Json -AsHashtable (available in PS 6.0+) (023-legacy-state-read-tolerance)
Local filesystem state files (JSON, YAML); paths: .specrew/, .specify/, .squad/, tasks-progress.yml (023-legacy-state-read-tolerance)
PowerShell 7.4+ (module code), Markdown (skill templates), PowerShell 5.1 Pester (integration tests) + Specrew PowerShell module (Specrew.psm1), Pester v5.3+, Git 2.40+ (024-slash-command-multi-host-correctness)
Filesystem (Specrew-managed skill deployments in .claude/skills/, .github/skills/, .agents/skills/, legacy .copilot/skills/), managed-marker detection via existing hygiene tooling (024-slash-command-multi-host-correctness)
PowerShell 7.0+ (per Specrew.psd1), Markdown skill templates with YAML frontmatter + Specrew PowerShell module/runtime scripts (Specrew.psm1, scripts/*.ps1, extensions/specrew-speckit/scripts/deploy-squad-runtime.ps1), Git, standard PowerShell file/YAML handling already used in-repo (024-slash-command-multi-host-correctness)
Filesystem only — source templates under extensions/specrew-speckit/squad-templates/skills/, active deployment targets .claude/skills/, .github/skills/, .agents/skills/, legacy migration target .copilot/skills/ (024-slash-command-multi-host-correctness)
PowerShell 7+ (primary runtime scripts), Markdown docs + Spec Kit CLI (specify), Squad CLI (squad), Git, module/runtime scripts under scripts/ and extensions/specrew-speckit/scripts/ (046-create-spec-branch)
File-based project artifacts (.specrew/, .specify/, .squad/, .github/) (046-create-spec-branch)

Read the full file on GitHub · 88 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.

2d ago First seen · 88 lines · 3,163 tokens per session scan A 338cdc72495b

Subscribe to this mod's changes

specrew copilot-instructions.md is an instructions file published in the GitHub repository alonf/specrew (54 stars, last pushed 4d ago), licensed MIT. It adds 3,163 tokens to every session, about $0.0158 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 2026-09-03.

Writing and docs

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

specrew: Instructions file for GitHub Copilot