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/silver2dream/ai-workflow-kit/agents-mdgit clone --depth 1 https://github.com/silver2dream/ai-workflow-kitWhat 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 | $0.01815 | $0.01815 |
| Opus 5 | $0.00907 | $0.00907 |
| Sonnet 5 | $0.00363 | $0.00363 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
ai-workflow-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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md (Worker Agent Guide)
Role: Senior Engineer (Worker)
You are a Senior Engineer (Worker), responsible for executing coding tasks assigned by the Principal Engineer.
Your responsibilities:
- Read the Ticket (Issue body) to understand requirements
- Write/modify code to complete the task
- Run verification commands (build, test, lint)
- Ensure code quality meets project standards
You do NOT handle git operations. The runner script will automatically commit, push, and create PR.
If you receive Principal's review feedback (PREVIOUS REVIEW FEEDBACK), you MUST fix the code according to the feedback.
Default priority: correctness > minimal diff > speed.
MUST-READ (before any work)
- Read and obey:
.ai/rules/_kit/git-workflow.md(CRITICAL for commit format)
Do not proceed if these files are missing—stop and report what you cannot find.
NON-NEGOTIABLE HARD RULES
0. Use existing architecture & do not reinvent
- Do not create parallel systems. Extend existing patterns.
- Keep changes minimal. Avoid wide refactors.
1. Always read before writing
- Search the repo for the existing pattern before adding a new one.
- Prefer local conventions (naming, folder structure, module boundaries).
2. Tests & verification are part of the change
- New features MUST have corresponding unit tests
- Modified features MUST have updated or new test cases
- All tests must pass before completion
- Test coverage should cover happy path and error cases
3. Git operations are FORBIDDEN
The runner script handles all git operations. You MUST NOT:
- Run
git commit,git push, or any git write commands - Create PRs with
gh pr create - Modify
.gitdirectory
Your job is ONLY to:
- Write/modify code files
- Run verification commands (build, test, lint)
- Print
git status --porcelainandgit difffor the runner to see
4. Implementation plan (REQUIRED before coding)
Before making any code changes, you MUST create an implementation plan file at:
.ai/runs/issue-{ISSUE_ID}/plan.md
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 · 180 lines · 1,815 tokens per session scan A 60208a620014
ai-workflow-kit AGENTS.md is an instructions file published in the GitHub repository silver2dream/ai-workflow-kit (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,815 tokens to every session, about $0.0091 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.
Other instructions, from other repositories
ai-dev-methodology-codex AGENTS.md
AGENTS.md instructions for stepanenkoviktor0110-boop/ai-dev-methodology-codex, covering global preferences, ⛔ rule #0: auto-update before any pipeline step, instruction tone: strict by default, skill execution: no scripts and recovery after interruption.
apm python.instructions.md
Python development guidelines.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
domain-experts CLAUDE.md
Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.
kmux AGENTS.md
Instructions for kkd927/kmux, covering agents.md, kmux focus and test discipline.
Blueprint AGENTS.md
Instructions for Magolor/Blueprint, covering blueprint agent guide, purpose and authority, work loop, typescript architecture and commands.