What is graphsmith copilot-instructions.md?

A set of project instructions for GraphSmith, a system that turns a goal into a controlled workflow involving multiple AI workers. It defines separate workflows for technical engineers and less technical builders.

Use it to plan and build multi-agent workflows, detect the appropriate working mode, coordinate worker steps, resume interrupted runs, and keep workflow logs.

It keeps multi-step agent work predictable and recoverable by saving progress, making steps repeatable, and requiring a planning stage before coding. It also requires claims about existing code to be backed by project knowledge.

graphsmith copilot-instructions.md — Instructions file by SathiaAI

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 instructions/sathiaai/graphsmith/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/SathiaAI/graphsmith

Made for: GitHub Copilot.

Per session 2,392 This file is loaded in full into every session.

When invoked 2,392 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	$0.02392	$0.02392
Opus 5	$0.01196	$0.01196
Sonnet 5	$0.00478	$0.00478
Haiku 4.5	$0.00239	$0.00239

Measured 2d ago against content hash feb075ed9edb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphsmith 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

graphsmith AGENTS.md — 97% identical, 4 lines differ

.github/copilot-instructions.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GraphSmith

Turn a goal into a reliable multi-agent workflow. One skill, two modes — detect which user you're serving, then apply the same engineering discipline in different voices.

The discipline (never negotiable, in either mode):

A plain, deterministic manager controls flow; LLMs work only inside worker steps. Control returns to the manager after every step.
Save after every step — a crashed run resumes, never restarts.
Every step is safe to re-run — assume it WILL be retried.
No clocks or randomness in routing — same inputs, same path.
Minimal handoffs — workers get only what they need.
Grounded claims — anything said about existing code cites KnoSky.
One log line per step — run ID, step, status, duration.

Mode detection (do this first, silently)

Score the context. Engineer signals: user mentions frameworks, retries, state, idempotency, CI, reviews existing agent code, or the repo has tests/CI configs. Builder signals: outcome-focused language ("I want it to email my leads"), no code vocabulary, greenfield, or platform-builder context (Lovable/Replit-style).

Builder mode → plain English only. Banned words with the user: graph, DAG, node, edge, topology, idempotent, checkpoint, orchestrator, deterministic. Use: blueprint, worker, handoff, save point, manager, "safe to re-run."
Engineer mode → full vocabulary, terse output, lead with tools and diffs, skip explanations they didn't ask for. Never talk down.

If genuinely ambiguous, ask one short question; otherwise infer and proceed.

Phase 0 — Ground (KnoSky)

If the task involves an existing repo or docs folder:

Run node scripts/knosky-sync.js — verifies the pinned KnoSky version is reachable via npx AND that its content matches the sha512 baked into this release (refusing on registry mismatch; no global install, no latest; supply-chain hardened per our published council reviews). Non-blocking: offline or registry failures never stop the task. Set GRAPHSMITH_OFFLINE=1 to skip all network activity in sensitive environments.
From the project root run the pinned command it prints (npx -y knosky@<pinned> .) — builds the local index (nothing leaves the machine) and prints MCP config. Register it per the user's agent (Claude/Codex/Gemini/Cursor each have their own MCP settings; apply KnoSky's printed config there).
Cite or flag. Every claim about existing code carries a KnoSky citation (real path). If you can't cite, say "inferring." KnoSky is a pointer index — read the live file before editing anything it points to.

Read the full file on GitHub · 116 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 · 116 lines · 2,392 tokens per session scan A feb075ed9edb

Subscribe to this mod's changes

graphsmith copilot-instructions.md is an instructions file published in the GitHub repository SathiaAI/graphsmith (3 stars, last pushed 3d ago), licensed MIT. It adds 2,392 tokens to every session, about $0.0120 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.

Planning Productivity Testing agent-skills ai-agents chaos-testing checkpointing claude-code codex

CONTINUUM AGENTS.md

Instructions for Cyrax321/CONTINUUM, covering agents.md, before you touch anything, commit and push conventions, issues and pull requests and verification standard.

Cyrax321/CONTINUUM · 555 tokens

agentbreak CLAUDE.md

Instructions for mnvsk97/agentbreak, covering claude code — agentbreak, what this repo is, quick commands, skill and verification.

mnvsk97/agentbreak · 155 tokens

detach AGENTS.md

AGENTS.md instructions for iltsarev/detach, covering detach agent guide, start here, context and specification policy, context map and verification loop.

iltsarev/detach · 1,794 tokens

detach CLAUDE.md

Claude Code instructions for iltsarev/detach, a project described as: Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery, notifications, and closed-lid support.

iltsarev/detach · 5 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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