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 skills add kanfu-panda/pdlc-skills --skill pdlc-qualitygit clone --depth 1 https://github.com/kanfu-panda/pdlc-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kanfu-panda/pdlc-skills/pdlc-quality)<a href="https://agentmods.dev/skills/kanfu-panda/pdlc-skills/pdlc-quality"><img src="https://agentmods.dev/badge/skills/kanfu-panda/pdlc-skills/pdlc-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kanfu-panda/pdlc-skills/pdlc-quality"><img src="https://agentmods.dev/badge/skills/kanfu-panda/pdlc-skills/pdlc-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 28 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 28 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 5.1 | $0.00030 | $0.06854 |
| Opus 5.5 | $0.00012 | $0.02742 |
| Sonnet 5.5 | $0.00006 | $0.01371 |
| Haiku 4.5 | $0.00003 | $0.00685 |
Grade A, and why
pdlc-quality 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 1mo 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
质量闸门与报告
跑真实 check → 对照质量目标 → 出可核对的报告 → 人签字放行。
⛔ IRON LAW · 不可违反的硬门禁(工具型命令)
本命令不是主链路上的阶段:不追加 history,不改 current_stage / next_step / last_phase_result,也不为此分配功能ID。以下规则不可协商:
- 文件必须落盘:正文要求创建的文件必须作为实际文件写入磁盘,不可仅在对话中输出(只要求在对话里输出的,照正文办)。
- 自检必须执行:产出后按本命令的自检项逐项核对,不得以"已经很好了"为由跳过。
- 防循环:修复只做一次,不递归。修不了的问题记进报告,继续往下走。
违反任一条 = 立即中止当前命令,输出违规详情,等待人工介入。
非交互模式(--autonomous)
若本命令的参数含 --autonomous,本命令进入无人值守模式,按以下规则处理原本需要人应答的交互点。参数是唯一真源:不带 --autonomous 即为交互模式,一切照旧正常询问用户;绝不回读状态机 run_mode 兜底(「掉出 autonomous」是安全的失败方向)。
- 流程性确认(如「测试已绿是否继续」「是否覆盖已有文件」)→ 不询问,按预设默认前进,并把决策追加到状态机
history[].auto_decisions[](写状态机的命令:推进时给状态推进脚本传--decision "<确认点描述>=<所选默认>",可重复;脚本写成下面的样子):{ "point": "<确认点描述>", "chose": "<所选默认>", "at": "<ISO 8601>" } - 真需人判断(PRD 关键取舍、评审「需人工确认」项、真实循环依赖、测试与设计 / PRD 矛盾等无法安全默认的点)→ 不猜。
改测试、改检查命令让它变绿,永远不是「流程性默认」,不能记成
--decision:current_stage保持不变(不推进)- 写
last_phase_result.ok = false且blocked_reason = "<原因>"(写状态机的命令:给状态推进脚本传--blocked "<原因>") - 末行输出哨兵:
<<<PDLC blocked reason="<原因>">>> - 立即结束命令,交还人类
- 守卫拦截也走这一条:前置守卫(缺设计文档、缺测试、测试没红等)在
--autonomous下拦住本命令时, 不能只输出 ⛔ 就停——同样写ok=false+blocked_reason(写明哪条守卫、缺什么)并输出哨兵。 否则状态机里仍是上一阶段的ok=true,循环驱动只看到current_stage没动,会把「被拦」误报成「卡住」,真实原因丢失。
- 破坏性操作(发布 / 部署 / 打 tag / 触发 CI / DROP / force-push 等不可逆·外发操作)→
--autonomous无效,仍必须人工显式确认。 - 顺手的 sidecar 产物(如缺失时创建
CHANGELOG.md、补全文档 PDLC-TRACE 的创建时间等本阶段职责内、可安全默认的辅助改动)→ 视为流程性默认,直接做并记入auto_decisions[];这类改动不新增外部副作用,不属破坏性操作。
进入 autonomous 模式时,在状态机顶层写
run_mode: "autonomous"仅供留痕(复盘区分人工 vs 循环产出)。
这个命令的立身之本
一切判定来自客观数据:覆盖率数字来自覆盖率工具、E2E 覆盖来自 flow→test 映射 + 真跑结果、lint 来自退出码。 AI 只负责把这些数据整理成报告,不参与"达标与否"的判定,放行由人。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +2 lines · +30 tokens per session 105a8b4c6e69
- 1mo ago Changed · -3 lines 75a7bda84d9d
- 1mo ago Changed · +16 lines 03c981a0bb1c
- 1mo ago Changed · +122 lines 0d97e2ae1d4b
- 2mo ago First seen · 217 lines · 0 tokens per session scan A aadc77924f1c
pdlc-quality is a skill published in the GitHub repository kanfu-panda/pdlc-skills (18 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 6,854 once invoked, about $0.0001 per session on Opus 5.5. 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.
pdlc-quality compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pdlc-qualitykanfu-panda/pdlc-skills | Skill | 18 | 6d ago | MIT | A | 30 | Claude Code |
| postgres-database-migrationtimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 220 | Cursor |
| timescaledb-hyperfunctionstimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 298 | Cursor |
| design-postgis-tablestimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 31 | Cursor |
| setup-timescaledb-hypertablestimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 219 | Cursor |
| migrate-postgres-tables-to-hypertablestimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 181 | Cursor |
| pgvector-semantic-searchtimescale/pg-aiguide | Skill | 1.9k | 2d ago | Apache-2.0 | A | 190 | Cursor |