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 jscraik/Agent-Skills --skill sy-workgit clone --depth 1 https://github.com/jscraik/Agent-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/skills/jscraik/agent-skills/sy-work)<a href="https://agentmods.dev/skills/jscraik/agent-skills/sy-work"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/sy-work/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/jscraik/agent-skills/sy-work"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/sy-work.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 | $0.00614 |
| Opus 5 | $0.00018 | $0.00307 |
| Sonnet 5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
sy-work 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SynAIpse Harness Work
When to use
Use when an approved execution plan or explicit bounded task is ready for implementation.
Required inputs
- User request or routed handoff naming this stage.
- Current repository, branch, artifact, tracker, PR, validation, and session evidence when available.
- The previous-stage artifact when this stage depends on one.
Deliverables
- A stage result with schema_version, stage, status, evidence_refs, blocked_by, and next_stage.
- Exact validation status using pass, fail, or blocked.
- A handoff that names what is proven and what remains unproven.
Procedure
- Restate the active repo, branch, requested stage, and available evidence.
- Check the previous-stage artifact or explain why it is not required.
- Perform only the work owned by work.
- Record evidence refs and classify each lane as pass, fail, blocked, or not_checked.
- Emit the next-stage handoff to review or a blocker with the smallest recovery step.
Validation
Fail fast: stop at the first failed required gate, classify the blocker, and do not proceed to downstream stages until the failure is resolved or explicitly waived. Run the smallest relevant local check for changed files; for package-level changes, run plugin validation and SDK proof commands from the repository wrapper.
Handoff
Return the stage artifact or blocker, then hand off to review only after this stage's exit criteria are satisfied.
Failure modes
- Missing previous-stage artifact: block and request or create the required artifact through the owning stage.
- Conflicting evidence lanes: route to reconcile.
- Repeated failure or durable learning: route to reinforce.
- Requested action exceeds authority: block with the required authorization.
Gotchas
-
Do not use this stage to skip the lifecycle, merge evidence lanes, mutate external systems without explicit authorization, or complete another stage's exit criteria.
-
Similar legacy names may exist in caches or older Harness Engineering packages; do not expose them as SynAIpse active skills.
-
A local artifact can explain work, but it does not prove remote PR, CI, tracker, or deployment state.
-
If multiple stages seem plausible, route to sy-reframe instead of doing blended stage work.
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.
- 8d ago First seen · 68 lines · 36 tokens per session scan A e9440b494d0f
sy-work is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 36 tokens to every session and 614 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
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
public-repo-creation
Create production-ready public GitHub repositories with comprehensive documentation, automated setup, and quality assurance.
git-flow
A shared set of rules for common Git work, including commits, branches, pushes, merges, rebases, and pull requests. Git is the version-control system used to record and combine code changes.
prepare-pr
A pull-request preparation workflow for a software branch. A pull request is a request for teammates to review and merge a set of code changes.
release-readiness
Use when user asks if a release is ready to ship, needs a go/no-go decision, or wants to run quality gates before deploying.
deploy-local
End-to-end local deployment loop for Gitea-hosted projects. Use when the user wants to commit on dev, push to remote, monitor the golden CI/build/deploy workflow, validate prod on the configured prod host, and fix lint/test/pipeline failures until deployment is healthy.