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.
git clone --depth 1 https://github.com/dhslegen/digital-delivery-teamWrote 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/commands/dhslegen/digital-delivery-team/fix)<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/fix"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/fix/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/commands/dhslegen/digital-delivery-team/fix"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00027 | $0.01658 |
| Opus 5.5 | $0.00011 | $0.00663 |
| Sonnet 5.5 | $0.00005 | $0.00332 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade B, and why
fix scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null) How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fix
输入:$ARGUMENTS
修复 /verify(review-agent)产出的 docs/review-report.md 中已列出的问题。默认 dry-run——仅输出 diff 让用户 review;通过 --apply 才会真正写入。
Phase 1 — 前置校验
test -f docs/review-report.md || { echo "❌ docs/review-report.md 不存在,请先运行 /verify 或 /review"; exit 1; }
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT="${HOME}/.claude/plugins/marketplaces/digital-delivery-team"
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || { echo "❌ DDT plugin root 未解析。可能原因:(1) 插件未安装;(2) shell 中 DDT_PLUGIN_ROOT 指向无效路径,请 unset DDT_PLUGIN_ROOT 后重启会话;(3) 运行 /digital-delivery-team:doctor 自检"; exit 1; }
export DDT_PLUGIN_ROOT
if printf '%s' "$ARGUMENTS" | grep -q -- '--dry-run'; then
node "$DDT_PLUGIN_ROOT/bin/print-dry-run.mjs" --phase fix --inputs "docs/review-report.md,docs/blockers.md,git diff" --outputs "(修复 patch 应用于 web/ server/ docs/)" --next "/verify"
exit 0
fi
node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase fix --action start
"$DDT_PLUGIN_ROOT/bin/check-blockers.sh" || exit 2
Phase 2 — 解析参数
| 参数 | 默认 | 说明 |
|---|---|---|
--severity blocker|warning|all |
warning |
修复哪一级(阻塞 / 警告 / 全部) |
--apply |
关 | 真正写入文件;不传则 dry-run(仅输出 diff) |
--dry-run |
开 | 显式 dry-run(与无 --apply 等价) |
阻塞级永远要求用户 review patch,即使传 --apply 也必须逐条确认。
Phase 3 — 派发 fix-agent
使用 Task 工具派发 fix-agent,传入:
docs/review-report.md(待修复条目)docs/api-contract.yaml(修改后端时必读)docs/data-model.md(修改持久层时必读)$ARGUMENTS(severity 与 apply 标志)
fix-agent 产出:
- 受影响源码的 Edit/MultiEdit
docs/review-report.md追加## Fix Log段落
Phase 4 — 自动回归
# 后端
test -d server && (cd server && (npm test --silent 2>/dev/null || make smoke 2>/dev/null || true))
# 前端
test -d web && (cd web && (npm test --silent --run 2>/dev/null || true))
任一回归失败 → 提示重跑 /fix 或 /verify:
❌ 修复后回归失败,请检查 fix-agent 产出的 patch
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 First seen · 160 lines · 27 tokens per session scan B bbae48a54cd8
fix is a command published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,658 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised with fixes, and kept improvements. Shadow-first; never auto-pushes. Runs on-demand or scheduled for off-hours.
bug-blitz
Emit and fire a canonical bug-backlog queue grind; dispatch, don't defer.
doctor
Diagnose a Rami install — checks auth, GitHub App coverage, quota, and plugin version.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
perf
Diagnose and fix a performance problem measurement-first — baseline, profile, numeric target, implement, re-measure.