Apollo Mode
v1.0.0开启或关闭工程师模式,让AI按规范流程工作。 开启或关闭工程师模式,让AI按规范流程工作:先定目标,写规格、拆任务、小步执行、最后验收。
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's declared purpose (enable/disable an engineering workflow) matches its instructions (reading/writing a local state file, producing specs/plans, using bundled templates). Minor metadata inconsistencies exist: the skill is named 'Apollo Mode' in registry but internal metadata and state filename use slug 'sysflow-mode' and the _meta.json ownerId differs from the registry ownerId — likely packaging/renaming noise but worth verifying.
Instruction Scope
SKILL.md only instructs the agent to read/write a single state file (memory/sysflow-mode.md), produce specs/plans, and follow a coding workflow for coding tasks. It does not instruct reading arbitrary system files, environment variables, or contacting external endpoints. Note: the state file is persistent and will remain in agent memory/storage.
Install Mechanism
No install spec and no code files to execute — instruction-only skill, so nothing is downloaded or written during install.
Credentials
Requires no environment variables, credentials, or config paths. The requested capabilities are proportional to the described functionality.
Persistence & Privilege
always:false and user-invocable:true (typical). The skill will create/update a persistent state file (memory/sysflow-mode.md) under the agent's memory — this is expected for a mode toggle but you should be aware the state persists across sessions and could be read/modified by other agent components.
Assessment
This is an instruction-only workflow toggle that appears internally consistent: it doesn't request secrets, install software, or call external endpoints. Before installing, verify the metadata mismatch (skill name 'Apollo Mode' vs internal slug 'sysflow-mode' and differing ownerId) is expected by the publisher. Be aware it writes a persistent state file (memory/sysflow-mode.md) to agent storage — if you prefer no persistent flags, decline or inspect/clear that file after use. Allow autonomous invocation only if you trust the skill to toggle itself during coding tasks (autonomous invocation is the platform default).Like a lobster shell, security has layers — review code before you run it.
latest
Apollo Mode (On-demand)
Use this only when the user explicitly asks to enable/disable this mode, or when mode is already enabled for coding tasks.
State file
Track mode in:
memory/sysflow-mode.md
Format:
enabled: true|false
updatedAt: <ISO>
notes: <optional>
Commands
- Enable phrases:
включи sysflow,enable sysflow,sysflow on- Write
enabled: trueto the state file. - Confirm in 1 short message.
- Write
- Disable phrases:
выключи sysflow,disable sysflow,sysflow off- Write
enabled: false. - Confirm in 1 short message.
- Write
- Status phrases:
статус sysflow,sysflow status- Read state and report enabled/disabled.
Workflow when enabled (coding tasks only)
For coding/build/debug requests, follow this order:
- Clarify objective and constraints quickly.
- Produce a short spec (chunked, easy to review).
- Produce an implementation plan with small tasks.
- (Optional, 30 sec) Run a mini risk review:
- How can this fail in production?
- What is the weakest dependency/state assumption?
- What signal will show regression + how to rollback fast?
- Execute task-by-task (prefer test-first for risky changes).
- Verify against acceptance criteria, then summarize outcome + next step.
Use templates from references/ when useful.
Red flags (quick self-check)
If you notice these thoughts, slow down and apply the workflow:
- "Сейчас быстро вкачу без плана" for non-trivial changes.
- "И так понятно, тесты потом" on risky edits.
- "Откат не нужен" before touching config/auth/cron/system files.
- "Похоже работает" without explicit verification.
Guardrails
- Do not force this workflow for non-coding chat.
- If user asks for speed (
quick,без плана,just do it), skip to minimal plan and execute. - Keep updates concise; avoid process spam.
Comments
Loading comments...
