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 dsheard/cobol-o-matic --skill verify-cobol-artifactsgit clone --depth 1 https://github.com/dsheard/cobol-o-maticWrote 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/dsheard/cobol-o-matic/verify-cobol-artifacts)<a href="https://agentmods.dev/skills/dsheard/cobol-o-matic/verify-cobol-artifacts"><img src="https://agentmods.dev/badge/skills/dsheard/cobol-o-matic/verify-cobol-artifacts/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/dsheard/cobol-o-matic/verify-cobol-artifacts"><img src="https://agentmods.dev/badge/skills/dsheard/cobol-o-matic/verify-cobol-artifacts.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 | $0.00044 | $0.01266 |
| Opus 5 | $0.00022 | $0.00633 |
| Sonnet 5 | $0.00009 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
verify-cobol-artifacts 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COBOL Artifact Verification Recipes
Use these recipes to verify that analysis artifacts accurately reflect the source code. Each recipe specifies what to check, where to check it, and what constitutes a pass or fail.
Verify Transaction IDs (transactions)
Claim: Business-rules frontmatter says transactions: ["XXXX"]
Verification steps:
- Grep the source for any variable with TRANID or TRANSID in its name:
Grep pattern: "TRANID|TRANSID" on the program source - Read the VALUE clause -- it must match the frontmatter value exactly.
- Cross-check: grep for
EXEC CICS RETURN.*TRANSID-- the TRANSID variable should resolve to the same value. - Cross-check: if CSD files exist, grep for
DEFINE TRANSACTIONto confirm the mapping.
Pass: VALUE matches frontmatter. All cross-references agree.
Fail: VALUE differs from frontmatter, or no TRANSID found but
frontmatter claims one. Log as correction_needed.
Verify Call Relationships (calls, called_by)
Claim: Frontmatter says calls: ["PROGNAME"]
Verification steps:
- Grep the source for
CALL ':Grep pattern: "CALL '" on the program source - Every literal in CALL statements should appear in the
callslist. - For
called_by: check the caller's source forCALL 'THIS-PROGRAM'.
Pass: All CALL targets match. called_by is consistent with callers'
calls lists.
Fail: Missing CALL target in frontmatter, or called_by references a
program that doesn't actually CALL this one. Also check XCTL and LINK.
Verify File I/O (reads, writes)
Claim: Frontmatter says reads: ["ACCTDAT", "CUSTDAT"]
Verification steps:
- Grep for actual I/O operations:
Grep pattern: "EXEC CICS.*(READ|WRITE|REWRITE|DELETE)|OPEN.*(INPUT|OUTPUT|I-O|EXTEND)" on the source - For CICS: extract
FILE(x)orDATASET(x)from each match. For batch: extract file names from OPEN statements and cross-reference with SELECT...ASSIGN. - Resolve variable names against DATA DIVISION VALUE clauses.
- Compare resolved names against frontmatter
readsandwrites.
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.
- 12d ago First seen · 154 lines · 44 tokens per session scan A b25c013593b2
verify-cobol-artifacts is a skill published in the GitHub repository dsheard/cobol-o-matic (5 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,266 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 2026-08-31.
Other skills, from other repositories
ile-cobol-docs
IBM ILE COBOL 7.4/7.5 — language structure, four divisions, data description, file handling, DB2, debugging.
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.