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.
git clone --depth 1 https://github.com/jaskaranhundal/usap-skillsWrote 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/jaskaranhundal/usap-skills/compare)<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/compare"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/compare/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/jaskaranhundal/usap-skills/compare"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/compare.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 | $0.00036 | $0.00562 |
| Opus 5 | $0.00018 | $0.00281 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
compare 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a before/after comparison for zero-day-response.
Phase 1 — v1 Baseline (pre-fix)
- Read
tests/fixtures/zero-day-response-v1.mdin full. - Read
tests/scenarios/fortigate-zero-day.jsonin full. - Apply the scenario using only v1's reasoning procedure — do not import knowledge from v2.
- Produce abbreviated output covering only the sections relevant to the 6 known problems:
- How actions are expressed (intent blocks vs raw CLI)
- AWS lateral movement attack path
- Okta session theft handling
- Logging change recommendations
- Immediate traffic control options
- Any vendor-specific syntax used
- For each of the 6 problems, identify and quote the specific v1 text that demonstrates the failure (or note its absence).
Phase 2 — v2 Fixed (current)
- Read
response/zero-day-response/SKILL.mdin full. - Apply the same FortiGate scenario using v2's reasoning procedure.
- Produce equivalent abbreviated output sections for direct comparison with Phase 1.
- For each of the 6 problems, quote the specific v2 text that demonstrates the fix.
Phase 3 — Scorecard Table
Output the following comparison table:
Before/After Scorecard — zero-day-response
==========================================
| Problem | v1 (pre-fix) | v2 (fixed) |
|--------------------------------------|---------------|---------------|
| P1: Raw CLI commands in output | FAIL | PASS |
| P2: AWS IAM prerequisite missing | FAIL | PASS |
| P3: Okta theft without TLS check | FAIL | PASS |
| P4: No logging pre-flight | FAIL | PASS |
| P5: No immediate traffic controls | FAIL | PASS |
| P6: Incorrect vendor syntax | FAIL | PASS |
|--------------------------------------|---------------|---------------|
| TOTAL | 0/6 | 6/6 |
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.
- 9d ago First seen · 63 lines · 36 tokens per session scan A 24c7240a4d3f
compare is a command published in the GitHub repository jaskaranhundal/usap-skills (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 562 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.