Borrowing it
Nothing to install: this file belongs to SoftwareFoundationGroupAtKyotoU/pure-borrow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SoftwareFoundationGroupAtKyotoU/pure-borrow/main/.codex/skills/haskell/SKILL.mdgit clone --depth 1 https://github.com/SoftwareFoundationGroupAtKyotoU/pure-borrowWrote 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/softwarefoundationgroupatkyotou/pure-borrow/haskell)<a href="https://agentmods.dev/skills/softwarefoundationgroupatkyotou/pure-borrow/haskell"><img src="https://agentmods.dev/badge/skills/softwarefoundationgroupatkyotou/pure-borrow/haskell/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/softwarefoundationgroupatkyotou/pure-borrow/haskell"><img src="https://agentmods.dev/badge/skills/softwarefoundationgroupatkyotou/pure-borrow/haskell.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 | $0.00102 | $0.00989 |
| Opus 5.5 | $0.00041 | $0.00396 |
| Sonnet 5.5 | $0.00020 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
haskell 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haskell Development Super-Skill
This is the entry point for Haskell development in this repository. It coordinates the
Codex skills with the agent-agnostic repository policy in AGENTS.md:
- Hoogle lookup maps to
.codex/skills/hoogle. - Haddock dependency documentation lookup maps to
.codex/skills/haddock. - Formatting maps to
.codex/skills/haskell-format,.codex/skills/haskell-cabal-gild, and the shared hooks under.agents/hooks/. - Prefer HLS when available before falling back to full Cabal builds.
Ground Rules
- Use cabal nix-style builds.
cabal.projectandcabal.project.localare the source of truth. - Do not use
stackor invokeghcdirectly for normal validation. - In a multi-package project, work on and build one package at a time with
cabal build <pkg>. Get it green before moving to another package. - Format changed
.hs,.lhs, and.hsigfiles with thehaskell-formatskill before compiling. - Format changed
.cabal,cabal.project,cabal.project.local, andcabal.project.freezefiles with thehaskell-cabal-gildskill before compiling. - Prefer
(<>)over(++)for all concatenation, including lists and strings. - Quantify lifetime type parameters as
α,β,γ, with primes or numeric suffixes as needed; do not use prose lifetime names such aslifetime,scope, orinner. - Never call
unsafePerformIO(orunsafeDupablePerformIO,unsafeThaw,unsafeIOToST) in adirect…benchmark baseline. Write the plain-vectorbaseline withmodify, which takes aforall s. MVector s a -> ST s ()and handles thaw/freeze itself; useSTReffor auxiliary mutable state. See the benchmark section ofAGENTS.md. - After changing any Haskell source, run
cabal build alland thencabal testbefore committing. The plain build must come first: the doctest suite reads the built library. Keep-O2(pinned incabal.project); the inspection suite asserts optimized-Core properties that hold vacuously at-O1. - There is no
package.yaml/hpack in this repository; edit.cabalfiles directly.
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 · 68 lines · 102 tokens per session scan A 902429d0f760
haskell is a skill published in the GitHub repository SoftwareFoundationGroupAtKyotoU/pure-borrow (63 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 102 tokens to every session and 989 once invoked, about $0.0004 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 2026-10-02.
haskell compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| haskellSoftwareFoundationGroupAtKyotoU/pure-borrow | Skill | 63 | 1mo ago | BSD-3-Clause | A | 102 | Codex |
| dotnet-reversezhaoxuya520/reverse-skill | Skill | 44k | 1mo ago | MIT | A | 144 | Claude Code |
| dart-run-static-analysisflutter/agent-plugins | Skill | 3.2k | 2d ago | BSD-3-Clause | A | 43 | Claude Code |
| agents-sdk-dotnet-debuggingmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 136 | Claude Code |
| memory-optimizationbenchflow-ai/skillsbench | Skill | 1.9k | 2d ago | Apache-2.0 | A | 60 | Claude Code, Codex |
| golang-error-handlingsamber/cc-skills-golang | Skill | 3.8k | 5d ago | MIT | A | 144 | Claude Code |
| prismer-python-debugpyPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 19 | Claude Code, Codex |