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 skills/dean0x/devflow/apply-decisionsnpx skills add dean0x/devflow --skill apply-decisionsgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00033 | $0.01114 |
| Opus 5 | $0.00016 | $0.00557 |
| Sonnet 5 | $0.00007 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
apply-decisions 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Decisions
Canonical consumer algorithm for the DECISIONS_CONTEXT index passed by orchestrators. The index lists each ADR/PF entry with ID, truncated title, status, and area — not the full body. Use this skill to surface the right decisions and pitfalls for your task without loading the entire corpus.
Iron Law
VERBATIM IDs ONLY — NEVER FABRICATE
Cite only IDs that appear verbatim in DECISIONS_CONTEXT. If an ADR/PF ID is not in the index, do not cite it. If an entry looks relevant but you haven't Read its full body, do not cite it. Fabricated citations are worse than no citations.
5-Step Algorithm
Step 1: Scan the index
Read through all entries in DECISIONS_CONTEXT. The index format is:
Decisions (N):
ADR-001 Title truncated to 60 chars [Active]
ADR-002 Another decision [Active]
Pitfalls (M):
PF-004 Background hook god scripts [Active] — src/assets/scripts/hooks/foo.cjs
PF-011 DECISIONS_CONTEXT fan-out [Active] — src/assets/commands/...
ADR-NNN entries live in {worktree}/.devflow/learning/decisions.md
PF-NNN entries live in {worktree}/.devflow/learning/pitfalls.md
Read the relevant file and locate the matching `## ADR-NNN:` or `## PF-NNN:` heading for the full body.
Step 2: Identify plausibly-relevant entries
From the index, identify entries whose title or area plausibly overlaps with:
- The files you are modifying or reviewing
- The category of issue you are addressing (e.g., error handling, hook scripts, JSON parsing)
- The architectural area of your change
Titles are truncated to 60 characters — if a truncated title looks relevant, proceed to Step 3.
Step 3: Read the full body
For each plausibly-relevant entry, use the Read tool to open the decisions file listed in the DECISIONS_CONTEXT footer and locate the matching ## ADR-NNN: or ## PF-NNN: heading. Read the full section to confirm relevance and understand the decision or pitfall completely.
The footer is the single source of truth for file paths. Never substitute hardcoded paths — the footer resolves to the correct worktree, which may differ from your cwd in multi-worktree flows.
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.
- yesterday First seen · 101 lines · 33 tokens per session scan A 811ee73ed450
apply-decisions is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,114 once invoked, about $0.0002 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 skills, from other repositories
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更，检测文档同步状态，评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构，生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.