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 sqlew-io/sqlew-plugin --skill sqlew-pr-adrgit clone --depth 1 https://github.com/sqlew-io/sqlew-pluginWrote 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/sqlew-io/sqlew-plugin/sqlew-pr-adr)<a href="https://agentmods.dev/skills/sqlew-io/sqlew-plugin/sqlew-pr-adr"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-pr-adr/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/sqlew-io/sqlew-plugin/sqlew-pr-adr"><img src="https://agentmods.dev/badge/skills/sqlew-io/sqlew-plugin/sqlew-pr-adr.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 | $0.00085 | $0.01016 |
| Opus 5 | $0.00043 | $0.00508 |
| Sonnet 5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
sqlew-pr-adr 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 11d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REQUIRED: Enrich PRs with Decision Context
When creating a pull request, reviewers need WHY context, not just what changed. MUST query sqlew for decisions related to the actual code changes and group the PR description by decision.
Step 1: Get the Diff
# Get changed files and content vs base branch
git diff <base-branch>...HEAD --stat # File list
git diff <base-branch>...HEAD # Full diff
Extract keywords from the diff:
- File paths: directory names, module names (e.g.,
auth,migration,database) - Function/struct names: key identifiers added or modified
- Package/import changes: new dependencies or module references
Step 2: Reverse-Lookup Decisions via Suggest
For each extracted keyword, query sqlew to find related decisions:
suggest { action: "by_context", key: "<keyword>" }
suggest { action: "by_context", key: "<module-name>", tags: ["<relevant-tag>"] }
For each matched decision key, fetch full context:
decision { action: "get", key: "<matched-key>", include_context: true }
This retrieves: Rationale, Alternatives Considered, Tradeoffs.
Selection rules:
- Include decisions with score >= 35 from suggest results
- Deduplicate across keyword searches
- Cap at 5 decisions (keep PR readable)
- Skip deprecated decisions
Step 3: Group Files Under Decisions
Organize the PR body so each decision/constraint lists its related files directly.
REQUIRED markers (hook-enforced): The
sqlew pr-adrPreToolUse hook blocksgh pr createunless the body contains the literal heading## Architecture Decisionsor## Other Changes. Put every decision/constraint under## Architecture Decisionsas###subsections, and unattributed changes under## Other Changes. A PR whose changes are all tied to ADRs still needs the## Architecture Decisionsheading present.
## Summary
<!-- 1-3 bullet points: what this PR does overall -->
## Architecture Decisions
### Decision: <title> (<reason>)
- `path/to/file1.ts`: what changed and why
- `path/to/file2.ts`: what changed and why
### Decision: <another title> (<reason>)
- `path/to/file3.ts`: what changed and why
### Constraint: <rule description>
- `path/to/file4.ts`: what changed to comply
## Other Changes
<!-- Changes not tied to any Decision/Constraint -->
- `path/to/file5.ts`: minor cleanup
## Test Plan
- [ ] Test step 1
- [ ] Test step 2
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.
- 11d ago First seen · 140 lines · 85 tokens per session scan A d679d69c3fd9
sqlew-pr-adr is a skill published in the GitHub repository sqlew-io/sqlew-plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,016 once invoked, about $0.0004 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 skills, from other repositories
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
docs-update-from-diff
Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.
prepare-pr
Prepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
triage
Gatekeep and review GitHub issues and pull requests for Qwen Code maintainers. Use for GitHub Action issue triage, PR admission checks, product-direction review, KISS-focused PR review, and staged bilingual GitHub comments.
git-github-flow
Use for branch prep, clean commits, PR descriptions, GitHub issue triage, changelogs, release notes, review response, merge readiness, or publishing a branch safely.