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 agentmods add skills/dynsoft-lab/software-as-content-sdk/codexnpx skills add dynsoft-lab/software-as-content-sdk --skill codexgit clone --depth 1 https://github.com/dynsoft-lab/software-as-content-sdkWhat 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 | $0.00038 | $0.02100 |
| Opus 5 | $0.00019 | $0.01050 |
| Sonnet 5 | $0.00008 | $0.00420 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
sac-interaction scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"requires": { "bins": ["curl", "codex"] }, How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaC Interaction for Codex
Use SaC when Codex should present complex engineering analysis as an interactive app instead of a long markdown answer. The best Codex/SaC demos are developer workbenches: repo architecture maps, release readiness dashboards, PR/CI triage, migration plans, logs, test failures, and risk reviews.
Do not use SaC for short answers, simple code edits, or ordinary chat.
Infrastructure boundary (read first)
SaC server lifecycle is not your responsibility. You are a publish client, not an operator. Do not:
- restart, stop, or kill servers/processes
- change ports or migrate to a different port
- run test suites or debug unrelated infrastructure
- inspect or modify the repo unless the request explicitly asks for engineering analysis or code changes
If /inbox is unreachable (connection refused), follow this diagnostic
sequence:
Step 1 — Connectivity check. Run a lightweight health probe first:
curl -sS --connect-timeout 5 http://127.0.0.1:18420/health
If this returns {"status":"ok"}, the server IS running and curl GET
works. The POST failure is likely caused by payload construction, shell
quoting, --data-binary @- piping, or a POST-specific environment
restriction. Skip to Step 3 to use a more robust transport.
If this also fails (connection refused), the server is truly down. Continue to Step 2.
Step 2 — Start the server. Run sac serve exactly once:
sac serve
sac serve is idempotent and safe to run even if a server is already
running — it reuses a healthy one and exits, and refuses to fight a
contended port instead of producing a half-bound zombie. After sac serve,
retry the same POST with curl. If the retry succeeds, you are done.
Step 3 — Python fallback. If curl POST still fails but the health
check passed (or sac serve reported "already running and healthy"),
use Python urllib as an alternative transport. Write the full JSON
payload to a temporary file first so large markdown content with quotes,
backticks, and newlines is never shell-escaped:
What ships with it
1 file 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.
- yesterday First seen · 232 lines · 38 tokens per session scan A 8d394bf97fce
sac-interaction is a skill published in the GitHub repository dynsoft-lab/software-as-content-sdk (3 stars, last pushed 16d ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,100 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.