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 SkeneTechnologies/skene --skill build-implementationgit clone --depth 1 https://github.com/SkeneTechnologies/skeneWrote 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/skenetechnologies/skene/build-implementation)<a href="https://agentmods.dev/skills/skenetechnologies/skene/build-implementation"><img src="https://agentmods.dev/badge/skills/skenetechnologies/skene/build-implementation/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/skenetechnologies/skene/build-implementation"><img src="https://agentmods.dev/badge/skills/skenetechnologies/skene/build-implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 26 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high System Prompt Leakage · line 30 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium MCP Rug Pull · line 13 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 19 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 28 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00042 | $0.00527 |
| Opus 5.5 | $0.00017 | $0.00211 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
build-implementation 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 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
The CLI may present a menu (e.g. "Select option [1/2/3/4]"). Always pipe the option that shows the full prompt in the terminal (typically `3` for "Show full prompt"): Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
Build Implementation Prompt
Generate implementation prompts via the Skene CLI. The CLI generates the plan, not you.
Agent behavior rules
- Autonomous. Run the CLI, read the output, execute the implementation. No mid-flow questions.
- CLI is the source of truth. If
uvx skene buildfails, report the error. Do NOT write your own implementation plan as a substitute. - User cannot type into agent terminals. The agent handles all CLI input.
Steps
-
Discover CLI options Run
uvx skene build --helpto see available flags and understand any interactive prompts. -
Verify loop selection
ls .skene/active-loop.json 2>/dev/null || ls skene-context/growth-loops/ 2>/dev/null || ls skene/growth-loops/ 2>/dev/nullIf missing: "Run/skene-planfirst." Stop. -
Generate implementation prompt The CLI may present a menu (e.g. "Select option [1/2/3/4]"). Always pipe the option that shows the full prompt in the terminal (typically
3for "Show full prompt"):echo 3 | uvx skene buildIf the menu options differ from expected, check --help output or the terminal output to pick the "show/print prompt" option.
-
Read the prompt The CLI saves output to
skene-context/growth-loops/(legacyskene/growth-loops/). Read the full implementation prompt from the terminal output or that directory. -
Execute the prompt Start implementing the steps from the CLI-generated prompt directly. Present a brief summary of what will be done, then execute. Break large implementations into logical chunks.
-
Report completion "Implementation complete. Run
/skene-statusto validate."
Error handling
- CLI failure: Report error, suggest fix. Do NOT fabricate implementation plans.
- Stuck on menu prompt: Kill terminal, re-run with piped input.
- Permission errors: Give user the command for their terminal.
Output
Summary of what was implemented + "Run /skene-status to validate."
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 · 50 lines · 42 tokens per session scan A 9d9bf29824df
build-implementation is a skill published in the GitHub repository SkeneTechnologies/skene (126 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 527 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-session-search
Search, recover, inspect, export, and analyze local AI session history with AI Session Search (aise) across Claude Code, Claude Desktop local agent, Codex, Cursor, Antigravity, Pi coding agent, Prime Agent, Google AI Studio, and Gemini CLI. Use when asked to "find prior AI work", "recover context after compaction"…
cli2skill
Turn any CLI or MCP server into an Agent Skill. Use when you want to replace an MCP server with a zero-overhead CLI skill, or generate a skill from any command-line tool's --help output.
burnd-analyze-spend
Analyze your OpenClaw API spend — total cost, cost last 7 days, top cost leaks by model and provider, and concrete steps to reduce your bill. Use when the user asks about their AI spending, costs, budget, or which models are costing the most.
brain-log
Show brain sync and evolution history.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
healthcheck
System health monitoring and diagnostics - checks profClaw API, Redis, Docker, disk, memory, and processes with actionable status reports.