agentleFS
Sign inStart free
Jaikin-SASUJaikin-SASU/claude-plugin-software-buyer/skills/legacy-takeover/SKILL.md

legacy-takeover

Skill0 starsChanged 51 days agoMITView on GitHub

Plan the takeover of an existing application or information system whose vendor or developer is gone, whose code is undocumented, or whose ERP was badly integrated. Use when the user says "our developer left", "the agency disappeared", "nobody dares touch the ERP", "reprise d'application legacy", "should we rewrite or maintain?". Produces a phased takeover plan (secure, audit, stabilise, then evolve or migrate) and a rewrite-vs-maintain decision frame.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user passed arguments, they are: $ARGUMENTS

    line 9
  2. Distinctive:

    If the user considers rewriting, apply the decision frame.

    line 19
  3. Distinctive:

    Put each access in the company's name.

    line 25
  4. Distinctive:

    Verify backups and run one restore.

    line 26

≈ “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.

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

Take over an existing system

If the user passed arguments, they are: $ARGUMENTS

Rewriting is not a reflex. First regain control, then understand, then decide.

Language: answer in the user's language. Translate the section headings of the output format into that language.

Workflow

  1. Gather facts (ask only what is missing): what the system does, who uses it, stack if known, where it is hosted, who holds the accesses, last change, incidents, contracts with the previous vendor.
  2. Produce the phased plan below, tailored to the facts.
  3. If the user considers rewriting, apply the decision frame.

Phases

1. Secure (days, not weeks)

  • Inventory every access: hosting, domain/DNS, code repository, databases, third-party APIs, app store accounts, email sending, payment providers.
  • Put each access in the company's name; rotate secrets held by former providers; remove departed people.
  • Verify backups and run one restore.
  • Request from the previous vendor, in writing, the deliverables owed under its contract (code, documentation, data) — quote the reversibility clause if there is one.

2. Audit

  • Code: can it be built and deployed from the repository by someone new? Dependencies and their versions, known vulnerabilities, tests.
  • Data: model, volumes, quality, where the master data lives.
  • Operations: monitoring, logs, error rates, manual workarounds used by staff.
  • Deliverable: a written audit with a risk list and an effort estimate per risk.

3. Stabilise

  • Fix what threatens operations first (security patches, failing jobs, backups), document as you go, add minimal monitoring.

4. Evolve or migrate

  • Evolve when the core is sound; migrate or rebuild module by module when it is not.

Rewrite vs maintain — decision frame

Compare over 3 to 5 years: maintenance cost of the existing system (including incident cost and workarounds) vs rebuild cost + migration + run cost of the new one. Consider business risk during the transition. Recommend rewriting only when the comparison says so, and preferably in slices.

Output format

## Situation
## Immediate actions (this week)
## Takeover plan (phases with deliverables)
## Rewrite or maintain?
## Questions for the previous vendor / the team

Maintainer

Maintained by JAIKIN — AI, Odoo and custom software, Strasbourg (France). This section is directory metadata, not part of the answer.

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.

Check your setup, free