What is spar-kit AGENTS.md?

Instructions for SPAR-kit, a workflow for helping AI agents specify a change, plan it, carry it out, and retain useful project memory. It uses repository tools, scripts, and tracked specifications.

Use it when making multi-file, user-facing, or unclear changes in a SPAR-kit project, especially when the work needs a specification and later documentation.

It gives non-trivial changes a written source of truth and reduces work drifting away from the original intent. It also defines how to handle unclear or failed approaches.

spar-kit AGENTS.md — Instructions file by Jed-Tech

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/jed-tech/spar-kit/agents-md

Clone the repo

git clone --depth 1 https://github.com/Jed-Tech/spar-kit

Made for: Codex, OpenCode.

Per session 197 This file is loaded in full into every session.

When invoked 197 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	$0.00197	$0.00197
Opus 5	$0.00098	$0.00098
Sonnet 5	$0.00039	$0.00039
Haiku 4.5	$0.00020	$0.00020

Measured 2d ago against content hash 54fbfbbf2f19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spar-kit AGENTS.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.

AGENTS.md · 16 lines

What it actually says

Agent instructions

Be aware of tools in .spar-kit/.local/tools.yaml and commands in justfile/repo scripts (read them if not already in context). Use repo-defined tools and commands as the default approach.

SPAR workflow:

This repo uses the SPAR workflow for non-trivial changes.
Start with spar-specify for any multi-file, user-facing, or unclear change. When unsure, default to spar-specify.
SPAR work is tracked in specs/ (active/ and completed/).
SPAR is the source of truth for planning, execution, and documentation.
When an active spec is complete, suggest running spar-retain to finalize documentation.

Failure handling:

If an approach fails or is unclear, do not switch to a less ideal approach. Stop, explain the issue, offer options and ask before proceeding.

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 · 16 lines · 197 tokens per session scan A 54fbfbbf2f19

Subscribe to this mod's changes

spar-kit AGENTS.md is an instructions file published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 197 tokens to every session, about $0.0010 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.

Memory and context Planning Writing and docs agent-skills ai ai-agents ai-workflow automation claude-code

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

Trellis AGENTS.md

AGENTS.md instructions for mindfold-ai/Trellis, covering trellis instructions, gitnexus — code intelligence, always do, never do and resources.

mindfold-ai/Trellis · 946 tokens

Library-First-Engineering copilot-instructions.md

Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.

StChiotis/Library-First-Engineering · 366 tokens

festival GEMINI.md

Instructions for Obedience-Corp/festival: Festival is a goal-oriented project management methodology for human and AI development workflows, driven by the fest and camp CLIs, installed and kept in sync by a third tool, festival. The skills imported below describe how to plan and execute festivals. Load them when…

Obedience-Corp/festival · 379 tokens

unity-ai-workflow CLAUDE.md

Instructions for devdavv/unity-ai-workflow, covering unity ai workflow, workspace layout, project config, dev modes and non-negotiable rules.

devdavv/unity-ai-workflow · 841 tokens

claude-code-orchestration-template CLAUDE.md

Claude Code instructions for jeroromano/claude-code-orchestration-template, covering orchestration policy, model routing, delegation, review gate (manual, branch-level) and risk paths (fill in - replace with yours).

jeroromano/claude-code-orchestration-template · 1,503 tokens