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/jyyyyyt/dev-report-weekly/agents-mdgit clone --depth 1 https://github.com/JYYYYYT/dev-report-weeklyWhat 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 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
dev-report-weekly 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.
What it actually says
DevWeek contribution guide
Product boundary
DevWeek is a local-first desktop tool that turns selected Git evidence into an auditable weekly report. The product is not a generic chat wrapper: deterministic evidence collection and validation stay in the application, while the model is used only for synthesis.
Frozen visual direction
- Preserve the current information architecture, spacing, typography, neutral palette, rounded geometry, and motion language.
- Product work may add loading, empty, error, and evidence states, but must not redesign the existing four-step flow or sidebar.
- Reuse shadcn/ui primitives from
src/components/uifor interactive controls. Avoid one-off native form controls or new global CSS. - Any intentional visual change requires a before/after browser check at 1280 × 800.
Trust and privacy
- Never send repository data to an AI provider before the evidence review step.
- Never persist API keys. Persist only non-secret preferences.
- Every completed-work claim generated by AI must reference one or more valid evidence IDs.
- Execute Git with an argument array, never through an interpolated shell command.
Quality gates
Run pnpm check and cargo test --manifest-path src-tauri/Cargo.toml before merging.
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 · 24 lines · 253 tokens per session scan A 9e269a7e17e7
dev-report-weekly AGENTS.md is an instructions file published in the GitHub repository JYYYYYT/dev-report-weekly (49 stars, last pushed 13d ago), licensed Apache-2.0. It adds 253 tokens to every session, about $0.0013 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
Octop AGENTS.md
Instructions for TencentCloud/Octop, covering agents.md, 1. collaboration principles, think before writing, simplicity first and surgical edits.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
Lody AGENTS.md
Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
Vibelution AGENTS.md
Instructions for CCDawn/Vibelution, covering vibelution agent rules, 1. identity and priority, 2. global red lines, 3. start and routing and 3.0 每任务先 router.
Jarvis CLAUDE.md
Instructions for Szesnasty/Jarvis, covering jarvis — full project plan, 1. what is jarvis, 1a. source of truth doctrine, 2. target users and 3. key use cases.