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 ArabelaTso/Skills-4-SE --skill verified-spec-code-mappergit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/verified-spec-code-mapper)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/verified-spec-code-mapper"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/verified-spec-code-mapper/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/arabelatso/skills-4-se/verified-spec-code-mapper"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/verified-spec-code-mapper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 418 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00094 | $0.03505 |
| Opus 5.5 | $0.00038 | $0.01402 |
| Sonnet 5.5 | $0.00019 | $0.00701 |
| Haiku 4.5 | $0.00009 | $0.00350 |
Grade A, and why
verified-spec-code-mapper 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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verified Spec-Code Mapper
Overview
Establish explicit, evidence-based traceability between formal specifications and verified code components. Generate structured reports that map each specification to its implementation and correctness proofs, supporting verification auditing, documentation, and reproducibility.
Mapping Workflow
Step 1: Identify Specifications
Locate all formal specifications in the codebase:
-
Preconditions:
- Coq:
forall ... -> P -> ...(hypothesis before conclusion) - Dafny:
requiresclauses - Isabelle:
assumesclauses - Look for: Input constraints, safety conditions
- Coq:
-
Postconditions:
- Coq:
... -> Q(conclusion of theorem) - Dafny:
ensuresclauses - Isabelle:
showsclauses - Look for: Output guarantees, correctness properties
- Coq:
-
Loop Invariants:
- Dafny:
invariantclauses in loops - Coq: Lemmas about recursive functions
- Look for: Properties maintained across iterations
- Dafny:
-
Class/Type Invariants:
- Dafny:
predicate Valid()methods - Coq: Well-formedness predicates
- Look for: Structural constraints, consistency properties
- Dafny:
-
Functional Correctness:
- Theorems stating what function computes
- Equivalence to specification
- Look for: Correctness lemmas, specification theorems
Step 2: Map to Code Components
For each specification, identify corresponding code:
-
Direct mapping:
- Specification mentions function/method name
- Theorem statement references definition
- Example:
Lemma factorial_positive : forall n, factorial n >= 1→ Maps tofactorialfunction
-
Contextual mapping:
- Specification in same file/module
- Comments linking spec to code
- Naming conventions (e.g.,
sort_correct→sort)
-
Structural mapping:
- Preconditions → Function parameters
- Postconditions → Return values
- Invariants → Loop bodies or class fields
-
Record locations:
- File path
- Line numbers
- Function/method/class names
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 · 491 lines · 94 tokens per session scan A 920f39fb9f08
verified-spec-code-mapper is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (260 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,505 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 2026-09-03.
Other skills, from other repositories
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
clinical-reports
Creates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
nwb-conversion
Converts neuroscience acquisition data to Neurodata Without Borders files with NeuroConv and PyNWB, preserves metadata and timebases, checks evidence-based clock alignment, and produces schema validation, NWB Inspector findings and round-trip checks. Use for NWB conversion and synchronization of planar single-channel…
sync-submission
Use when building, auditing or freezing a journal submission package from the canonical manuscript. Detects drift between the source and the per-journal submission copy, builds byte-preserving packages with manifests, and records current, stale or frozen status.
ape-write-paper
Writes a polished, standard two-column research paper (LaTeX to PDF) from any source material -- code, docs, experiment logs, benchmark files, notes -- optimising for correctness, readability, structure, figures, tables and references. Supports both standalone papers and conference templates (ACM SIGMOD/VLDB, IEEE…