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 jazzyalex/agent-sessions --skill sc-skillgit clone --depth 1 https://github.com/jazzyalex/agent-sessionsWrote 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/jazzyalex/agent-sessions/sc-skill)<a href="https://agentmods.dev/skills/jazzyalex/agent-sessions/sc-skill"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/sc-skill/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/jazzyalex/agent-sessions/sc-skill"><img src="https://agentmods.dev/badge/skills/jazzyalex/agent-sessions/sc-skill.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 | $0.00055 | $0.00769 |
| Opus 5.5 | $0.00022 | $0.00308 |
| Sonnet 5.5 | $0.00011 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
sc-skill 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC Skill
Overview
Use this skill to produce repeatable screenshots for two modes:
testing: stable evidence screenshots for QA/regression workflows.marketing: polished, consistently framed screenshots for docs/site/release assets.
This skill is macOS-first and uses Peekaboo as primary automation with native screencapture fallback.
Quick Start
- Normalize window size and position:
skills/sc-skill/scripts/sc_window_preset.sh --app "AgentSessions" --preset marketing
- Capture one screenshot (auto-select tool):
skills/sc-skill/scripts/sc_capture.sh \
--app "AgentSessions" \
--mode marketing \
--delay 0.25 \
--max-edge auto \
--window-preset auto \
--output artifacts/screenshots/agent-sessions-main.png
- Run a manifest batch:
skills/sc-skill/scripts/sc_capture_suite.sh \
--manifest skills/sc-skill/references/examples/agent-sessions.tsv \
--outdir artifacts/screenshots
Workflow
- Choose mode:
testing: prioritize determinism and speed.marketing: prioritize composition consistency.
- Choose tool:
- Start with
--tool auto(defaults to Peekaboo when available and permitted). - Use
--tool nativewhen you need zero external dependency and simple window-region capture.
- Enforce layout before capture:
- Always run
sc_window_preset.shfirst. - Use consistent presets across runs to reduce visual drift.
- Capture and archive:
- Save to
artifacts/screenshots/.... - Sidecar metadata (
.json) is opt-in via--metadata; default runs keep artifacts cleaner. - Default output uses mode-based max edge (
--max-edge auto):testing=1800,marketing=2560, optimized/compressed for sharing/upload. - AgentSessions windows are normalized to a realistic working preset before capture (mode-based
testing/marketing) to avoid distorted/compressed UI composition. - Single capture closes the target app window by default (
--no-close-windowto keep it open). - Suite runs close captured app windows after all requested screenshots by default (
--no-close-after-suiteto keep them open). - For
AgentSessions, transcript readiness retry includes a built-in selection nudge (key down +0.5spause) to force transcript loading before capture. - Default transcript readiness remains fast-fail if loading still does not occur after nudge attempts.
- If transcript readiness times out, capture fails fast by default; pass
--allow-blank-transcriptonly when blank transcript output is acceptable.
What ships with it
7 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.
- 1mo ago First seen · 80 lines · 55 tokens per session scan A 158a890ed7dc
sc-skill is a skill published in the GitHub repository jazzyalex/agent-sessions (909 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 769 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
do-it-verify
Use when selecting evidence for a delivery claim, regression fix, installation, or branch closeout.
evidence-first-debugging
Use when debugging a crash, lỗi, failing game, tool, build, service, script, or reproducible local code failure requires repro or reproduction, giả thuyết or ranked hypotheses, instrumentation, root-cause isolation, a minimal fix, regression proof, and a regression test.
load-soak-capacity-verification
Use when servers or online game services need controlled load, soak, concurrency, capacity, saturation, leak, queue, failover, recovery, and scaling verification with baselines and stop conditions; not for client frame budgets.
platform-device-compatibility-matrix
Use when a game needs a platform and device compatibility matrix across OS, hardware, GPU, memory, resolution, input, network, storefront, certification, test evidence, and support policy; not for store metadata preparation.
qa-test-strategy-and-coverage
Use when a game project, milestone, or feature needs a QA test strategy and coverage matrix across risk, test levels, platforms, environments, ownership, automation, regression, evidence, and exit criteria; not for one playtest session.
release-candidate-preflight
Use when a release candidate or RC needs a go/no-go readiness decision across required artifacts, test summaries, known issues, approvals, compatibility, monitoring, and rollback.