agentleFS
br3eze-codebr3eze-code/br3eze-code/skills/agentos-engineer/SKILL.md

agentos-engineer

Skill3 starsChanged 5 days agoApache-2.0View on GitHub

Execute safe AgentOS engineering workflows for diagnostics, technical baselines, risk analysis, bounded code or configuration changes, tests, rollback, deployment proposals, and operational handoff. Use for debugging, implementation planning, infrastructure changes, and technical verification.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to investigate and prepare the smallest safe technical change.

    line 8
  2. Very specific:

    Create a stable activity such as ACT-ENGINEER-WP-ENG-004.

    line 35
  3. Very specific:

    Use diagnostics.read, code.read, code.propose, and tool.execute.

    line 41
  4. Distinctive:

    Never run a destructive command, expose credentials, modify another tenant’s resource, or deploy an unreviewed change.

    line 43
  5. Distinctive:

    Keep activity, logs, approvals, and audit records tenant-scoped and restart-safe.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AgentOS Engineer

Use this skill to investigate and prepare the smallest safe technical change. Require authenticated identity, tenant, project, site, domain, authorized environment, and explicit scope before reading or modifying systems.

Workflow

inspect current state
→ record technical risks and dependencies
→ define smallest safe change
→ define verification and rollback
→ request approval when mutation is required
→ execute in authorized environment
→ test and capture evidence
→ hand over with rollback readiness

Use:

ENG-001 inspect current state
→ ENG-002 analyse risks and rollback
→ ENG-003 implementation and verification plan
→ ENG-004 approved implementation and test
→ ENG-005 handover and rollback evidence

Activity and evidence

Create a stable activity such as ACT-ENGINEER-WP-ENG-004. Include baseline references, affected resources, dependency status, expected outcome, acceptance criteria, change scope, test plan, rollback plan, logs, evidence references, and approval ID.

A technical completion requires reproducible evidence: test output, changed files or configuration references, deployment identifier where applicable, observed result, unresolved defects, and rollback status. Do not mark implementation complete from a successful API response without verification.

Permissions and approvals

Use diagnostics.read, code.read, code.propose, and tool.execute. Require approval for code.write, config.write, deploy, and device.mutation. Recheck tenant, identity, capability, environment, and approval immediately before mutation. Rule-based shortcuts must use the same guard as model tool calls.

Never run a destructive command, expose credentials, modify another tenant’s resource, or deploy an unreviewed change. Prefer dry-run, backup, scoped target selection, idempotency, and rollback.

Collaboration

Receive requirements and acceptance criteria from Planner and Designer. Ask Draftsman for controlled technical documents. Provide Procurement with bill-of-material or technical compatibility inputs. Provide QA with tests and evidence. Give Secretary and Project Manager a customer-safe status summary, risks, next action, and decision required.

Outputs

Return:

verified baseline
root cause or bounded hypothesis
risk and dependency analysis
smallest safe change
approval requirement
verification plan
rollback plan
execution result
unresolved issues
handoff and evidence references

Keep activity, logs, approvals, and audit records tenant-scoped and restart-safe. Render the same activity number and execution status in all supported channels.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.