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/darkcofy/sqlprism/implementing-issuesnpx skills add darkcofy/sqlprism --skill implementing-issuesgit clone --depth 1 https://github.com/darkcofy/sqlprismWhat 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 | $0.00072 | $0.01008 |
| Opus 5 | $0.00036 | $0.00504 |
| Sonnet 5 | $0.00014 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
implementing-issues 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 today.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementing Issues
Workflow
Copy this checklist and track progress:
Implementation Progress:
- [ ] Step 1: Read issue and understand scope
- [ ] Step 2: Create branch and draft PR
- [ ] Step 3: Break down into tasks
- [ ] Step 4: Execute tasks (parallel where possible)
- [ ] Step 5: Verify and finalize
Step 1: Read Issue
gh issue view <number> --json title,body,labels,milestone
Extract from the issue body:
- Scenarios — the acceptance criteria
- Test Plan — test function names and files
- Dependencies — blocked by / blocks
If the issue is blocked by open issues, stop and inform the user.
Step 2: Create Branch and Draft PR
Follow the branch/PR naming convention: <type>-<issue_number>-<short-description>
Type mapping: enhancement → feat, bug → fix, chore → chore
git checkout main && git pull origin main
git checkout -b <type>-<number>-<description>
git push -u origin <type>-<number>-<description>
Create a draft PR immediately so progress is visible:
gh pr create --draft \
--title "<type>-<number>-<description>" \
--body "$(cat <<'EOF'
Closes #<number>
## Summary
- <to be updated on completion>
## Test Plan
<copy Test Plan table from issue, add Status column set to pending>
EOF
)"
Step 3: Break Down into Tasks
Analyze the issue scenarios and create a task breakdown. Save to .claude/plans/<issue_number>/tasks.json.
mkdir -p .claude/plans/<issue_number>
See TASK-FORMAT.md for the JSON schema and decomposition rules.
Key rules:
- Each task maps to one or more scenarios from the issue
- Tasks that touch different files/modules can run in parallel
- Tests are a separate task per module, but run after implementation tasks
- Every task has a clear "done when" that maps back to a scenario
Step 4: Execute Tasks
Read .claude/plans/<issue_number>/tasks.json and identify which tasks can run in parallel (no shared files, no dependency between them).
What ships with it
2 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.
- today First seen · 137 lines · 72 tokens per session scan A 3a9a6ed56baa
implementing-issues is a skill published in the GitHub repository darkcofy/sqlprism (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,008 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…