SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill gnucobol-mainframe-batchgit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/gnucobol-mainframe-batch)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/gnucobol-mainframe-batch"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gnucobol-mainframe-batch/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/benchflow-ai/skillsbench/gnucobol-mainframe-batch"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/gnucobol-mainframe-batch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00472 |
| Opus 5 | $0.00020 | $0.00236 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
gnucobol-mainframe-batch 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 9d 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.
What it actually says
GnuCOBOL mainframe batch
Compile and run
cobc -x -free -o prog PROG.cbl
./prog
-free allows *> comments and free-form source. File names in SELECT
are resolved relative to the program's run directory.
SELECT DETAIL-FILE ASSIGN TO "TRAN.DAT"
ORGANIZATION IS SEQUENTIAL.
For 80-byte fixed-record tapes use ORGANIZATION IS SEQUENTIAL with
RECORD CONTAINS 80 CHARACTERS in the FD. Pad WRITE records to the
required length (e.g. MOVE SPACES TO BAL-REC before populating fields).
PIC and signed amounts
When a tape stores sign and magnitude in separate positions (PIC X plus
PIC 9(11)V99), build a signed working-storage value before ADD /
SUBTRACT. Using only the unsigned magnitude in EVALUATE branches is a
frequent bug when debits and credits share the same magnitude field.
COMPUTE … ROUNDED rounds half away from zero in GnuCOBOL (matches the
Python Decimal ROUND_HALF_UP behaviour). Use it when multiplying a
two-decimal amount by a four-decimal rate and storing into a two-decimal
field.
Debug loop
cobc -x -free -Wall -o prog PROG.cblDISPLAYintermediate values for one or two records to confirm the posting math and any cross-file lookups.- Reconcile against a short script that applies the task's posting rules to the same tape layout.
References
- GnuCOBOL programmer's guide
- IBM Enterprise COBOL language reference for PIC/USAGE and file control when porting z/OS sources
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.
- 9d ago First seen · 54 lines · 40 tokens per session scan A 9c36434ae137
gnucobol-mainframe-batch is a skill published in the GitHub repository benchflow-ai/skillsbench (1,754 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 472 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
scala-circe-json
Working with Circe JSON library in Scala for type-safe JSON processing.
scala-adt-enums
Translating Python Enums and Protocols to Scala sealed traits and algebraic data types.
scala-collections-fp
Scala collections, iterators, and functional programming patterns for Python developers.
scala-option-either
Translating Python's None/Optional to Scala's Option, Either, and Try types.
mandarin-rhyming-guide
Master modern Mandarin pinyin finals and tone systems to create accurate rhymes for classical poetry following contemporary pronunciation standards.