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/haddock/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/haddock)<a href="https://agentmods.dev/skills/softwarefoundationgroupatkyotou/pure-borrow/haddock"><img src="https://agentmods.dev/badge/skills/softwarefoundationgroupatkyotou/pure-borrow/haddock/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/haddock"><img src="https://agentmods.dev/badge/skills/softwarefoundationgroupatkyotou/pure-borrow/haddock.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 | $0.00073 | $0.00906 |
| Opus 5.5 | $0.00029 | $0.00362 |
| Sonnet 5.5 | $0.00015 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
haddock 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Haskell Haddock And Source Reader
Read documentation and source code for dependencies of a cabal nix-style project, preferring local files over the network. Exhaust local sources before fetching from Hackage.
Which Source To Use
- Package is a dependency of the current project: read locally.
- Package is outside the project's dependency set: fall back to Hackage.
- Prefer the
hoogleskill for symbol or type lookup before fetching full documentation pages.
One-Time Setup
If local docs are missing, enable documentation and build once after dependency changes:
cabal configure --enable-documentation
cabal build all
Resolving A Dependency
Run the bundled resolver from the project root:
.codex/skills/haddock/scripts/locate-dep.sh <package>
The resolver regenerates the build plan, reads cabal's store and repo-cache paths, looks up the package's exact UnitId in dist-newstyle/cache/plan.json, and prints JSON:
{
"store_path": "<cabal-store>/<UnitId>",
"doc_dir": "<store_path>/share/doc/html",
"source": "<repo-cache>/.../<pkg>-<ver>.tar.gz"
}
store_pathis the resolved unit directory in the cabal store.doc_diris the Haddock HTML directory, ornullif docs were not built.sourceis a Hackage/Stackage source tarball path, source-repository-package metadata, ornull.
Do not construct store paths from package names. Cabal abbreviates and hashes store entries, so use the resolved UnitId.
Reading Docs
When doc_dir is non-null, module pages sit directly inside it. A module page is its dotted name with . replaced by - plus .html, for example System.Random.SplitMix becomes System-Random-SplitMix.html. Use index.html or list *.html files if the module name is uncertain.
Reading Source
For a string tarball path, stream a single file without unpacking everything:
tar -tzf <source>
tar -xzOf <source> <pkg>-<ver>/<path/to/File.hs>
For a source-repository-package object, use its { type, location, tag, subdir } metadata. Cabal checks the repo out under dist-newstyle/src/ in a directory named from the repo plus a content hash, not from the tag. Locate the source with a glob such as:
What ships with it
1 file 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.
- 1mo ago First seen · 88 lines · 73 tokens per session scan A 4259627704e7
haddock is a skill published in the GitHub repository SoftwareFoundationGroupAtKyotoU/pure-borrow (63 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 73 tokens to every session and 906 once invoked, about $0.0003 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.
haddock compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| haddockSoftwareFoundationGroupAtKyotoU/pure-borrow | Skill | 63 | 1mo ago | BSD-3-Clause | A | 73 | Codex |
| erlang-otp-behaviorsbenchflow-ai/skillsbench | Skill | 1.9k | 2d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| omh-rustrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 74 | Claude Code, Codex |
| axiom-concurrencyCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 49 | Claude Code |
| tddcodewithmukesh/dotnet-claude-kit | Skill | 805 | 2d ago | MIT | A | 81 | Claude Code |
| splitting-oversized-modulesPostHog/posthog | Skill | 41k | yesterday | none | A | 197 | Claude Code, Codex |
| precisemicroprediction/precise | Skill | 338 | 5d ago | MIT | A | 76 | Claude Code, Codex |