plugin-runtime-guardian
Skill2 starsChanged 7 months agoMITView on GitHub
Standardize diagnosis and fix backend runtime errors for plugins on Android glibc-runner (command not found, version verify fail, plugin-local mismatch, restart deferred). Use when log reports plugin runtime setup failed or backend not showing READY.
In this repository47 other files it gives its agents.
- brainstormingSkill
- claude-code-termux-runbookSkill
- cli-patcherSkill
- code-review-workflowSkill
- commit-commandsSkill
- consulting-analysisSkill
- context7-cleanSkill
- data-analysisSkill
- deep-researchSkill
- edit-tool-compat-guardSkill
- env-managerSkill
- executing-plansSkill
- feature-devSkill
- firecrawlSkill
- frontend-designSkill
- gateway-device-pairingSkill
- githubSkill
- glibc-prebuilt-bundleSkill
- gogSkill
- image-generationSkill
- memory-setupSkill
- module-auditorSkill
- module-scaffoldSkill
- openclaw-config-guardianSkill
- openclaw-ollama-runtime-kbSkill
- plugin-cutover-guardianSkill
- python-env-managerSkill
- self-improving-agentSkill
- simplify-and-hardenSkill
- skill-benchSkill
- skill-creatorSkill
- skill-unificationSkill
- skill-vetterSkill
- socratic-groundingSkill
- subagent-orchestrationSkill
- systematic-debuggingSkill
- tailscale-oauth-bridgeSkill
- termux-packagerSkill
- termux-runnerSkill
- test-driven-developmentSkill
- vercel-deploy-claimableSkill
- verification-before-completionSkill
- video-generationSkill
- workspace-cleanupSkill
- writing-plansSkill
- yt-dlp-ingest-firstSkill
- zero-downtime-cutoverSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 9 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Before any restart/status conclusion, the local Android module contract must be reconciled.
- Very specific: line 31
Do not report PASS if the new status is only registered but not ready after the actual restart/apply.
- Very specific: line 32
If the runtime issue follows a plugin shadow/update flow, do not assume --profile proved plugin filesystem isolation.
- Distinctive: line 41
Only performance/health warnings are not related to backend init.
- Distinctive: line 43
If you need to operate outside the workspace or network write beyond the required user range, checkpoint approval is required.
- Distinctive: line 57
Do not set string commands with args.
- Distinctive: line 58
If CLI needs fixed args => create separate executable wrapper.
- Very specific: line 63
Verify <wrapper> --version returns parseable semver (x.y.z).
- Distinctive: line 68
If the backend depends on a separate subsystem (e.g.
- Very specific: line 70
If the log has requires gateway restart ...
- Very specific: line 71
Before restart/status, compare against the local Android module contract.
- Distinctive: line 72
Only conclude PASS after restart + verify again.
- Distinctive: line 83
Avoid JS wrapper/echo noise.
- Distinctive: line 85
Check the latest runtime/plugin-specific env dependency and log stack.
- Distinctive: line 89
Do not debug it as a normal runtime readiness bug first.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plugin Runtime Guardian
Indexed Reference Map
- @[SKILL.md#L1-L95] Frontmatter + trigger + SOP + output contract
- @[references/runbook.md#L1-L72] Generic diagnostic matrix + fix decision tree
- @[scripts/verify_plugin_backend.sh#L1-L67] Runtime verification script (plugin-aware)
Scope
- In-scope:
- Plugin runtime backend is not READY.
- Log signatures:
runtime setup failed,command not found,parseable version,plugin-local ... mismatch,requires gateway restart ... deferring. - Standardize command executable path + wrapper discipline.
- Out-of-scope:
- Change plugin/OpenClaw upstream code.
- Fix channel/provider error unrelated to backend runtime plugin.
Hard Rules
- Temp verify artifacts, filtered logs, wrapper probes must be in
workspace/.ops/tmp/<task-id>/. - Metadata/checkpoint/report files must be in
workspace/.ops/state/<task-id>/. - Before any restart/status conclusion, the local Android module contract must be reconciled; prioritize
openclaw.service ...when the lifecycle action is absolutely necessary. - Do not report PASS if the new status is only
registeredbut notreadyafter the actual restart/apply. - If the runtime issue follows a plugin shadow/update flow, do not assume
--profileproved plugin filesystem isolation; verify the resolved install/discovery path before treating the shadow candidate as valid evidence.
Trigger Rules
- Positive:
- User provides startup plugin log with
runtime setup failed. - User requests to fix backend plugin (acpx or similar plugin) that failed verification.
- Plugin
registeredbut noready.
- User provides startup plugin log with
- Negative:
- Just install the regular package, without the runtime backend plugin.
- Only performance/health warnings are not related to backend init.
- Escalation:
- If you need to operate outside the workspace or network write beyond the required user range, checkpoint approval is required.
SOP
- Snapshot runtime
openclaw status --deep- Collect the most recent log from the canonical runtime log path; temp captures saved under
workspace/.ops/tmp/<task-id>/.
- Classify failure signature (according to
references/runbook.md):- A)
plugin-local binary unavailable/mismatched - B)
command not found at <path-or-string> - C)
--version output did not include a parseable version - D)
config change requires gateway restart ... deferring - E)
shadow/plugin isolation mismatch(config/state looked isolated, but install/discovery path still touched live plugin root)
- A)
- Enforce command contract (critical)
- Plugin command must be single executable path.
- Do not set string commands with args.
- If CLI needs fixed args => create separate executable wrapper.
- Create canonical wrapper (when needed)
- Standard shell shebang (
#!/system/bin/shon Android). exec <absolute-runtime-binary> <absolute-cli-entry> "$@".chmod 755.- Verify
<wrapper> --versionreturns parseable semver (x.y.z).
- Standard shell shebang (
- Patch config deterministic
plugins.entries.<plugin>.enabled = trueplugins.entries.<plugin>.config.command = <wrapper-or-binary-absolute-path>plugins.entries.<plugin>.config.expectedVersion = <installed-version>(if plugin has verified version)- If the backend depends on a separate subsystem (e.g. acp), then the corresponding subsystem verify key is enabled.
- Restart semantics
- If the log has
requires gateway restart ... deferring, the status is PENDING_RESTART. - Before restart/status, compare against the local Android module contract; prioritize
openclaw.service ...if applicable. - Only conclude PASS after restart + verify again.
- If the log has
- Post-restart verification (required)
- There is
runtime backend registeredwith the new command. - There is
runtime backend ready. - There are no new
runtime setup failederrors for that plugin. openclaw status --deepis still healthy.
- There is
Error Handling
command not foundafter patch:- Re-check absolute path, executable bit, shebang compatibility.
version parse fail:- Avoid JS wrapper/echo noise; use pure exec shell, clean stdout.
registered but not ready:- Check the latest runtime/plugin-specific env dependency and log stack.
deferred restart:- Return status
PENDING_RESTART, do not report PASS early.
- Return status
invalid-isolation/ profile-only shadow leftover:- Do not debug it as a normal runtime readiness bug first.
- Classify it separately, remove or quarantine the incomplete shadow artifact, then retest with a dedicated shadow home.
Output Contract
- Deliverable:
- Root cause category (A/B/C/D).
- Config keys changed + old/new.
- Wrapper path +
--versiontest output. - Temp/state artifact paths if available.
- Log evidence before/after (registered/ready/failed).
- Validation:
PASS: hasregistered+ready, no new failures.PENDING_RESTART: config is correct but not restarted/applied completely.FAIL: restarted but still failed.
- Compliance Verdict:
PASS|PENDING_RESTART|FAIL+ short, unambiguous reason.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

