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 msrv-tech/skills --skill databasegit clone --depth 1 https://github.com/msrv-tech/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/msrv-tech/skills/database)<a href="https://agentmods.dev/skills/msrv-tech/skills/database"><img src="https://agentmods.dev/badge/skills/msrv-tech/skills/database/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/msrv-tech/skills/database"><img src="https://agentmods.dev/badge/skills/msrv-tech/skills/database.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 | $0.00028 | $0.00641 |
| Opus 5.5 | $0.00011 | $0.00256 |
| Sonnet 5.5 | $0.00006 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
database 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 27d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
34 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.
- agents/openai.yaml 251 B
- evals/evals.json 40 KB
- references/build-cf-patch.md 4.5 KB
- references/create.md 3.7 KB
- references/dump-cf.md 4.0 KB
- references/dump-xml.md 6.0 KB
- references/ibcmd.md 6.5 KB
- references/load-cf.md 4.2 KB
- references/load-git.md 4.6 KB
- references/load-xml.md 7.1 KB
- references/project-settings.md 2.0 KB
- references/repository-update.md 6.7 KB
- references/run.md 4.0 KB
- references/update.md 5.5 KB
- scripts/build-cf-patch.ps1 1.1 KB runs code
- scripts/build-cf-patch.py 14 KB runs code
- scripts/create.ps1 4.6 KB runs code
- scripts/create.py 4.2 KB runs code
- scripts/dump-cf.ps1 4.6 KB runs code
- scripts/dump-cf.py 3.7 KB runs code
- scripts/dump-xml.ps1 6.9 KB runs code
- scripts/dump-xml.py 5.7 KB runs code
- scripts/load-cf.ps1 4.6 KB runs code
- scripts/load-cf.py 3.7 KB runs code
- scripts/load-git.ps1 11 KB runs code
- scripts/load-git.py 10 KB runs code
- scripts/load-xml.ps1 8.9 KB runs code
- scripts/load-xml.py 8.2 KB runs code
- scripts/repository-update.ps1 7.7 KB runs code
- scripts/repository-update.py 9.9 KB runs code
- scripts/run.ps1 4.2 KB runs code
- scripts/run.py 2.6 KB runs code
- scripts/update.ps1 5.0 KB runs code
- scripts/update.py 3.9 KB runs code
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.
- 27d ago Changed · +1 lines 0edc998804ea
- 1mo ago First seen · 33 lines · 28 tokens per session scan A 16b66d0379b9
database is a skill published in the GitHub repository msrv-tech/skills (62 stars, last pushed 22d ago), with no licence file. It adds 28 tokens to every session and 641 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 2026-09-28.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
review-triage-phase
Produces canonical review actions from fetched review state and renders action markdown. Use when the user wants only triage/action-planning for the review-framework workflow.
multiline-commit-messages
Use single-quoted strings for multiline git commit messages in the Shell tool. Prevents heredoc escaping failures that produce garbled commit messages.
rule-engine-extract
Extract reusable migration rules from code changes. Works on interactive fixes (before/after comparison), git history, or any pair of SQL files. Triggers: extract rule, deduce rule, learn from fix, create rule from fix, rule extraction.
vdjdb-publish
Publish proofread VDJdb chunks through dev, reconcile publication issues, preserve record identity, keep validation changes separate, and close completed imports while tracking unresolved observations and optional metadata follow-ups. Use when a chunk is ready to publish or an imported paper needs closeout.