Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/oscal-compass-lab/compliance-trestle-skillsnpx agentmods add skills/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineeringWrote 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/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineering)<a href="https://agentmods.dev/skills/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineering"><img src="https://agentmods.dev/badge/skills/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineering/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/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineering"><img src="https://agentmods.dev/badge/skills/oscal-compass-lab/compliance-trestle-skills/oscal-document-engineering.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 | $0.00028 | $0.00823 |
| Opus 5 | $0.00014 | $0.00411 |
| Sonnet 5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
oscal-document-engineering 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSCAL Document Engineering
Use this skill when a user wants to turn old compliance documents into maintainable OSCAL. Typical outputs are SSPs, SAPs, SARs, POA&Ms, component definitions, and evidence packages.
Core rule
Every OSCAL statement must be traceable to source text, collected evidence, or a user-supplied assertion.
If the source is unclear, mark the item needs_review.
Do not invent a compliance fact.
Inputs
Common inputs:
- SSP in PDF, DOCX, Markdown, or text.
- Existing OSCAL JSON, XML, or YAML.
- Evidence folders, diagrams, inventories, policies, or POA&M spreadsheets.
- Framework or profile target such as FedRAMP Moderate, NIST 800-53, SOC 2, ISO 27001, or organization-specific profiles.
Outputs
Make these artifacts:
- OSCAL workspace or package.
source-traceability-map.csv.ssp-import-plan.md.import-summary.md.validation-report.jsonor a Markdown equivalent.unmapped-items.mdthat lists content that needs human review.
Workflow
- Make sure you know the source files and the target OSCAL document type.
- Make a workspace outside committed source unless you use a synthetic example.
- Extract text. Keep page numbers, headings, and section identifiers when possible.
- Build a source traceability map with
templates/source-traceability-map.csv. - Start or update a Compliance Trestle workspace.
- Draft a schema-valid SSP from extracted sections when Trestle is available:
bash plugins/document-transform/oscal-document-workbench/scripts/draft-ssp-from-extraction.sh <workspace> --overwrite
The FedRAMP Rev 5 heading map at plugins/document-transform/oscal-document-workbench/templates/fedramp-rev5-heading-map.json is an optional adapter for FedRAMP-style SSPs.
For SOC 2, ISO 27001, or other sources, keep unmatched sections needs_review.
Do not force FedRAMP field targets.
7. Refine mappings and fill remaining OSCAL SSP structure:
- metadata
- parties and roles
- system characteristics
- system implementation
- control implementation
- inventory items
- back matter resources
- Validate with Compliance Trestle and OSCAL CLI when available.
- Make summary reports and identify gaps.
- Ask the user or system owner to review all
needs_reviewitems.
What ships with it
5 files 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.
- 12d ago First seen · 95 lines · 28 tokens per session scan A 5a3d289d1d40
oscal-document-engineering is a skill published in the GitHub repository oscal-compass-lab/compliance-trestle-skills (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 823 once invoked, about $0.0001 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
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
akf-trust-metadata-v2
AKF — The AI Native File Format workflow skill. Use this skill when the user needs The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing and the operator should preserve…
executing-nist-rmf-authorization-to-operate
Drive a federal system through the NIST Risk Management Framework (SP 800-37 Rev 2) to an Authorization to Operate (ATO): Prepare, Categorize (FIPS 199), Select a control baseline (FIPS 200 / SP 800-53 Rev 5), Implement, Assess (SP 800-53A), Authorize, and Monitor continuously. Use when a system needs an ATO or a…
court-sms
A workflow that reads court text messages or delivery links, extracts case details, downloads court documents, and files them in the matching case folder.
chinese-copyright-application
A document-generation toolkit for preparing Chinese software copyright registration materials from a software project’s code and documentation. It supports applications for web apps, mobile apps, desktop software, and WeChat mini programs.
chinese-copyright-application-okooo5km
A document-generation tool for preparing Chinese software copyright registration materials from a software project. It creates a Markdown application form and LaTeX source files for a source-code document, user manual, and design description.