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/practicalswan/agent-skills/code-examples-syncnpx skills add PracticalSwan/agent-skills --skill code-examples-syncgit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWhat 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 | $0.00036 | $0.00936 |
| Opus 5 | $0.00018 | $0.00468 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
code-examples-sync 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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Example Synchronization
Use this skill when docs contain code snippets that are likely to drift from the real implementation.
- Leverage native parallel subagent dispatch and 200k+ context windows where available.
Activation Conditions
Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.
- Function signatures changed
- Imports or package names changed
- Request or response contracts changed
- Framework guidance or recommended patterns changed
- A doc snippet compiles conceptually but no longer matches the codebase
Workflow
- Find the canonical implementation first.
- Update every affected snippet in docs, examples, and READMEs.
- Verify syntax, imports, and expected outputs.
- Note any intentional divergence, such as simplified tutorial snippets.
Anti-Patterns
- Starting work before the plan or gate is clear: Execution drifts when success criteria are implied instead of explicit.
- Treating verification as optional cleanup: The last mile is where regressions and missing updates are usually hiding.
- Mixing planning, implementation, and release work in one jump: You lose the causal chain that explains why a change is safe.
Verification Protocol
Before claiming "skill applied successfully":
- Pass/fail: The Code Examples Sync workflow starts from explicit success criteria, constraints, and stop conditions.
- Pass/fail: Required evidence is collected before any completion, approval, or readiness claim.
- Pass/fail: The next action follows the documented gate order without skipping review or verification steps.
- Pressure-test scenario: Apply the workflow under time pressure with one failing check and one tempting shortcut.
- Success metric: Zero rationalizations; blocked, failed, or unverified work is reported as such.
Quality Checklist
- Snippet matches current API shape
- Imports and package names are current
- Async, error handling, and setup steps still make sense
- Output examples match current behavior
- Duplicate snippets across docs were updated together
What ships with it
4 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.
- 2d ago First seen · 95 lines · 36 tokens per session scan A 34b1178ff78e
code-examples-sync is a skill published in the GitHub repository PracticalSwan/agent-skills (11 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 936 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 2026-08-30.
Other skills, from other repositories
code-review
Automated code review with checklist and quality gates.
code-review
代码审查和质量分析技能。用于审查代码、发现潜在问题、提供改进建议。当用户请求代码审查、代码质量分析或最佳实践建议时使用。.
code-review
Reviews diffs by severity to produce actionable feedback.
refactoring
Safe, test-backed code restructuring in small steps.
requesting-code-review
Self-reviews work against the plan before sign-off.
test-writing
Writes meaningful tests that actually catch bugs.