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 commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidenceWrote 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/commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidence)<a href="https://agentmods.dev/commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidence"><img src="https://agentmods.dev/badge/commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidence/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/commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidence"><img src="https://agentmods.dev/badge/commands/oscal-compass-lab/compliance-trestle-skills/update-ssp-from-evidence.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 | $0.00496 |
| Opus 5 | $0.00014 | $0.00248 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
Update SSP From Evidence 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.
What it actually says
/oscal-document-workbench:update-ssp-from-evidence
Use new evidence, findings, or POA&M information to update an existing OSCAL SSP. Keep source traceability. This is an agent-led workflow. This is not a one-shot converter.
How to run
- Summarize the current source map:
node plugins/document-transform/oscal-document-workbench/scripts/summarize-source-map.js <workspace>/extracted/source-map.csv
Exit 3 means needs_review rows remain.
That is expected until review is complete.
- Add or update source-map rows for the new evidence.
Keep source hashes, targets, and
needs_reviewwhere the evidence is incomplete. - Update the SSP through the Trestle authoring roundtrip when possible. If a direct JSON edit is required, validate afterward.
- Rebuild the review queue:
bash plugins/document-transform/oscal-document-workbench/scripts/build-review-queue.sh \
<workspace>/extracted/source-map.csv \
--output <workspace>/reports/review-queue.md
- Validate:
bash plugins/document-transform/oscal-document-workbench/scripts/validate-oscal-package.sh \
<workspace>/trestle-workspace \
--output <workspace>/reports/validation-report.json
Arguments
<workspace>: import workspace withextracted/,trestle-workspace/, andreports/<source-map.csv>: current source traceability map
Outputs
- updated
source-map.csv - updated SSP model or markdown
reports/review-queue.mdreports/validation-report.json
Exit codes
0: summary has noneeds_reviewrows2: bad arguments or unreadable input3:needs_reviewrows remain or validation failed5: required external dependency is missing
Safety notes
- Keep source files unchanged.
- Maintain source traceability for every mapped OSCAL field.
- Mark uncertain mappings as
needs_review. - Do not treat structural validation as an audit opinion.
- Do not commit sensitive customer evidence or real SSPs.
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 · 70 lines · 28 tokens per session scan A 34dc221bffa9
Update SSP From Evidence is a command 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 496 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 commands, from other repositories
compare-versions
Compare two versions of an FRMR document.
isms-documentation-pack
Generate complete ISO 27001 ISMS documentation pack including mandatory and supporting documents.
FedRAMP SSP Convert
Convert FedRAMP Rev 5 SSP DOCX templates (main SSP + Appendix A) to OSCAL 1.2.0 SSP JSON.
ssp-guidance
System Security Plan (SSP) documentation guidance.
evidence-examples
Get evidence examples for FedRAMP compliance.
control-requirements
Get all requirements for a NIST control.