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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-create-diffgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-diff)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-diff"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-diff/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-diff"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-diff.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 | $0.00037 | $0.03466 |
| Opus 5 | $0.00018 | $0.01733 |
| Sonnet 5 | $0.00007 | $0.00693 |
| Haiku 4.5 | $0.00004 | $0.00347 |
Grade A, and why
sk-create-diff 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 5d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Diff
create-diff is the sk-doc workflow packet for reviewing what changed in a locally edited document — outside Git and without a hosted service. It captures a baseline before an edit, then compares the before and after versions and renders a single self-contained, accessible HTML report. The comparison engine ships with this packet as scripts/create_diff.py; everything runs on the machine with no network, no upload, and no telemetry, and source files are never modified.
Supported formats and fidelity tiers: plain text and Markdown (full text fidelity), HTML and DOCX (visible/structural text), and text-layer PDF (conditional on a local extractor). Each report states its fidelity tier so a comparison is never trusted beyond what the extractor can actually see.
This packet owns diff authoring and its two scripts. It uses shared sk-doc standards from ../shared/ for surrounding-document quality. It must not add packet-local advisor metadata such as graph-metadata.json or description.json.
1. WHEN TO USE
Activation Triggers
Use this packet when the request asks to:
- Review what an AI (or anyone) changed in a locally edited document.
- Produce a before/after report for a Markdown, text, HTML, DOCX, or PDF file that is not in Git.
- Capture a baseline of a document before editing it, so the change can be reviewed afterward.
- Compare two explicit versions of a document (an old file and a new file).
Keyword triggers: create diff report, document before/after review, before/after document diff, document change report, review document edits, docx diff, pdf diff.
When NOT to Use
Route elsewhere when:
- The files are code or already tracked in Git — use
git/sk-gitfor source diffs. - The comparison is visual or design-oriented (layout, pixels, screenshots) — out of scope; create-diff compares extracted text only.
- The task is auditing, scoring, or validating a single existing document rather than comparing two states — use
create-quality-control. - The deliverable is a README, skill, command, agent, changelog, or flowchart — use the matching
create-*packet.
What ships with it
39 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.
- assets/fixtures/onboarding-after.md 897 B
- assets/fixtures/onboarding-before.md 675 B
- assets/fixtures/README.md 1.3 KB
- changelog/v1.0.0.0.md 583 B
- changelog/v1.1.0.0.md 3.3 KB
- changelog/v1.1.1.0.md 1.6 KB
- changelog/v1.1.2.0.md 1.2 KB
- feature-catalog/comparison-engine/deterministic-diffing.md 3.3 KB
- feature-catalog/comparison-engine/multi-format-extraction.md 3.7 KB
- feature-catalog/comparison-engine/self-contained-report.md 4.2 KB
- feature-catalog/feature-catalog.md 6.3 KB
- feature-catalog/safety-and-capabilities/capability-tier-reporting.md 2.9 KB
- feature-catalog/safety-and-capabilities/report-safety-validation.md 2.8 KB
- feature-catalog/snapshot-lifecycle/baseline-snapshot-and-compare.md 3.1 KB
- feature-catalog/snapshot-lifecycle/explicit-pair-comparison.md 3.1 KB
- feature-catalog/snapshot-lifecycle/snapshot-state-management.md 2.7 KB
- manual-testing-playbook/comparison/docx-text-comparison.md 4.8 KB
- manual-testing-playbook/comparison/html-visible-text-comparison.md 4.9 KB
- manual-testing-playbook/comparison/markdown-before-after-review.md 4.7 KB
- manual-testing-playbook/comparison/pdf-text-comparison.md 5.5 KB
- manual-testing-playbook/manual-testing-playbook.md 16 KB
- manual-testing-playbook/safety/capability-and-unsupported-handling.md 5.2 KB
- manual-testing-playbook/safety/hostile-content-escaped.md 5.2 KB
- manual-testing-playbook/safety/self-contained-zero-js-report.md 5.0 KB
- manual-testing-playbook/safety/source-never-mutated.md 4.6 KB
- manual-testing-playbook/snapshot/baseline-capture-then-compare.md 5.0 KB
- manual-testing-playbook/snapshot/missing-baseline-fallback.md 4.8 KB
- manual-testing-playbook/snapshot/snapshot-status-and-cleanup.md 5.1 KB
- README.md 9.3 KB
- references/accessibility-contract.md 4.5 KB
- references/capabilities-and-fidelity.md 4.0 KB
- references/cli-reference.md 3.4 KB
- references/README.md 1.0 KB
- references/worked-example.md 2.7 KB
- references/workflow.md 3.9 KB
- scripts/create_diff.py 72 KB runs code
- scripts/README.md 3.9 KB
- scripts/test_create_diff.py 32 KB runs code
- scripts/validate_report.py 13 KB runs code
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.
- 5d ago First seen · 298 lines · 37 tokens per session scan A 91cf34e8834f
sk-create-diff is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 3,466 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 2026-09-03.
Other skills, from other repositories
pandoc-pdf-error-resolution
Systematic debugging workflow for pandoc PDF conversion errors.
pandoc-unicode-sanitize
Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion.
pdf-debug-unbuffered
Debug Python PDF generation errors by using unbuffered output and stderr inspection to reveal actual tracebacks.
python-shell-fallback
Fallback to shell execution when sandbox fails for library-dependent Python code.
pandoc-pdf-error-diagnosis
Systematic diagnostic workflow for resolving pandoc PDF conversion errors.
pandoc-pdf-error-recovery
Systematic approach to diagnose and recover from pandoc PDF conversion unknown errors.