Steer AI coding agents
before they make a mess.
A local-first CLI + Claude Code plugin that coaches engineers and non-technical builders through a disciplined workflow — Research, Propose, Plan, Implement, Test.
“Like a calm senior engineer sitting next to you in the terminal.”
What breaks agents
Everything your team works around is something that breaks an agent. Took audits your repo for exactly these gaps and frames every finding as a fixable thing.
$ took ready — runs an agent-readiness audit on your repo and produces a prioritised fix list. Free, local, no account needed.
The RePPIT loop
Research → Propose → Plan → Implement → Test. The six-step discipline that turns vague prompts into production-grade, verifiable code — and coaches you through every stage.
Produce the document the agent plans from. No research → no plan → slop.
Force alternatives. Only one solution considered is a red flag.
A reviewable spec with a verifiable done. The agent's contract.
Externalise progress on large tasks. Protect the context budget.
Favour automatic verification. Missing tests = untrusted code.
Pipp Health only. HIPAA/SOC2/HITRUST gate after Test.
Before the agent touches code, you (or Took) generate a research artifact: current API docs, existing patterns, affected files. Without it the agent hallucinates.
Took coaches you to produce at least two or three approaches with trade-offs before committing. Alternatives prevent tunnel vision and surface risk early.
A plan document scopes the diff before it happens: files in scope, files off-limits, acceptance criteria. Took checks the agent stays inside the lines.
Took guards each tool call — scope blowouts, dangerous commands, near-dumb-zone context warnings. Large tasks checkpoint progress to artifacts so nothing is lost to compaction.
Took's diff check catches missing test coverage and flags risky untested diffs. PR readiness scores tests as a first-class signal.
In regulated mode, a sixth gate runs compliance checklists against the diff. Loop Implement → Test → Secure until clean. A green diff never auto-passes what code can't prove.
Two-axis governor
Over-coaching is a failure mode too. Took scales how closely it watches to the task and the operator — so a one-line fix never gets the full loop, and a healthcare migration never skips the Secure gate.
Rigor ↔ Task Size
A one-line fix gets a light touch. A cross-service migration gets the full loop. Took never over-coaches trivia or under-coaches complexity.
Protection ↔ Operator
Engineers get Took in Coach mode. Non-technical builders default to Guard/Strict. Regulated teams get the Secure gate. Right-sized, not maximum.
One coach, three layers
Took is free for engineers. Pipp extends it for builders who want to understand what they're managing. Pipp Health adds regulated-industry compliance for healthcare teams.
Took
Engineer CoreSteer AI coding agents before they make a mess.
- ✓RePPIT workflow coaching
- ✓Pre-tool guard + diff review
- ✓Agent-readiness audit
- ✓Docs & playbook drift check
- ✓PR readiness score
- ✓Local XP ledger
Pipp
Education LayerBuild with AI and actually understand what's happening.
- ✓Plain-English narration of every agent action
- ✓Leveled, cited learning resources
- ✓Heightened scanning & guardrails
- ✓Concept tracking — stops re-explaining
- ✓Learning XP + profile
- ✓Free taste (N explanations/day)
Pipp Health
Regulated Add-onShip healthcare software with compliance checks built into the workflow.
- ✓Secure phase (RePPITS loop)
- ✓HIPAA / SOC 2 / HITRUST assessment
- ✓PHI/PII standing scan
- ✓Code-verifiable vs org controls
- ✓Retained compliance audit trail
- ✓Composable with Pipp
Install in your agent
Took works as a Claude Code plugin — hooking into UserPromptSubmit, PreToolUse, PostToolUse, and PreCompact events to coach without interrupting your flow.
Judgment rewarded, not tokens burned
Took XP rewards quality, judgment, and learning — never prompt count, diff size, or token volume. Right-sizing a task earns a Judgment bonus. Running the full loop when it was warranted earns Research, Plan, and Test XP.
Anti-gaming: per-category daily caps, evidence required (real artifacts, tests, surviving PRs), and improvement deltas rewarded over absolutes — so messy starters are rewarded for growth.
Generated a research doc before prompting
Scoped the diff with a verifiable done
Prevented a dangerous out-of-scope edit
All changed files have test coverage
Right-sized a trivial task, skipped loop
Mastered a new concept via Pipp
Start steering your agents.
Free local CLI. No account. No cloud. No surveillance. Just a calm senior engineer in your terminal.