Skip to content

stevesolun/ctx / docs

skill-router

Flagged

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

FileKindSize
SKILL.mdskill md9.3 KB
assets/javascripts/catalog.jsscript2.5 KB
assets/javascripts/repo-stats-refresh.jsscript3.2 KB
backup-hook-install.mdmarkdown9.2 KB
catalog.mdmarkdown10.3 KB
ctx-fit/ARCHITECTURE_CANDIDATES.mdmarkdown12.9 KB
ctx-fit/ARCHITECTURE_GAP_ANALYSIS.mdmarkdown10.7 KB
ctx-fit/CTX_AUDIT.mdmarkdown11.6 KB
ctx-fit/CURRENT_STATE.mdmarkdown16.3 KB
ctx-fit/DECISIONS.mdmarkdown15.7 KB
ctx-fit/GOOD_FIRST_ISSUES.mdmarkdown20.6 KB
ctx-fit/IMPLEMENTATION_TRACKER.mdmarkdown697 B
ctx-fit/MAP.mdmarkdown7.8 KB
ctx-fit/PRD.mdmarkdown9.7 KB
ctx-fit/STATE.mdmarkdown60.9 KB
ctx-fit/milestones/M1_SPIKE_FRICTION_LOG.mdmarkdown5.5 KB
ctx-fit/milestones/MILESTONE_00_AUDIT.mdmarkdown5.1 KB
ctx-fit/planned_tasks.mdmarkdown17.7 KB
dashboard.mdmarkdown24.7 KB
enterprise-readiness-review.mdmarkdown8.7 KB
entity-onboarding.mdmarkdown18.0 KB
harness/attaching-to-hosts.mdmarkdown16.2 KB
harness/clean-host-contract.mdmarkdown4.5 KB
harness/loopflow-adapter-demo.mdmarkdown11.1 KB
huggingface-publish.mdmarkdown3.3 KB
index.mdmarkdown22.4 KB
knowledge-graph.mdmarkdown22.7 KB
marketplace-registry.mdmarkdown4.0 KB
memory-anchor.mdmarkdown2.7 KB
plans/ctx-agent-reviewer-workbench.mdmarkdown12.4 KB
plans/unified-capability-engine.mdmarkdown59.0 KB
qa/dashboard-user-story-status.csvother26.0 KB
qa/feature-user-story-status.csvother92.5 KB
research/context-engineering-guidance-audit.mdmarkdown10.4 KB
services/macos/com.claude.backup.watchdog.plistother1.7 KB
services/systemd/claude-backup-watchdog.serviceother1.3 KB
skill-lifecycle-and-dashboard.mdmarkdown6.2 KB
skill-quality-install.mdmarkdown6.2 KB
skill-router/index.mdmarkdown2.5 KB
skill-stack-matrix.mdmarkdown5.5 KB
skills-health.mdmarkdown3.5 KB
stack-signatures.mdmarkdown6.2 KB
telemetry.mdmarkdown24.7 KB
threat-model.mdmarkdown15.0 KB
toolbox/behavior-miner.mdmarkdown2.6 KB
toolbox/configuration.mdmarkdown4.0 KB
toolbox/council-runner.mdmarkdown2.4 KB
toolbox/hooks.mdmarkdown2.6 KB
toolbox/index.mdmarkdown3.0 KB
toolbox/intent-interview.mdmarkdown3.0 KB
toolbox/starters.mdmarkdown3.0 KB
toolbox/templates/docs-review.jsonconfig599 B
toolbox/templates/fresh-repo-init.jsonconfig533 B
toolbox/templates/refactor-safety.jsonconfig634 B
toolbox/templates/security-sweep.jsonconfig636 B
toolbox/templates/ship-it.jsonconfig676 B
toolbox/verdicts.mdmarkdown4.0 KB

toolbox/council-runner.md

View on GitHub
# Council runner

[`src/council_runner.py`](https://github.com/stevesolun/ctx/blob/main/src/council_runner.py)
is the planner that turns a toolbox declaration into a concrete `RunPlan`
the hook system can execute.

## Responsibilities

1. **Resolve the toolbox** — merge global + per-repo config.
2. **Compute scope** — use explicit files, the current diff, the full repo,
   or one-hop graph expansion when a graph edge map is supplied.
3. **Carry budget caps** — copy the toolbox token and second caps into the
   plan so downstream execution can enforce them.
4. **Honor dedup** — reuse a cached plan when the toolbox policy is `cached`
   and the matching hash is still inside `dedup.window_seconds`.
5. **Persist** — write the plan to
   `~/.claude/toolbox-runs/<plan_hash>.json` for downstream reads.

## RunPlan

```python
@dataclass(frozen=True)
class RunPlan:
    toolbox: str
    agents: tuple[str, ...]
    files: tuple[str, ...]
    scope_mode: str
    budget_tokens: int
    budget_seconds: int
    guardrail: bool
    created_at: float
    plan_hash: str
    source: str           # "fresh" | "cached"
```

The `plan_hash` is deterministic from the toolbox, agents, file set, and
effective scope mode, which lets dedup work without any additional state.

## CLI

```bash
# Build and persist a plan for the named toolbox
python -m council_runner plan --toolbox ship-it

# Build without persisting (useful for inspection)
python -m council_runner plan --toolbox ship-it --dry-run

# List recent plans
python -m council_runner history --limit 10

# Delete stale plans
python -m council_runner purge --older-than-days 30
```

## Budget estimation

The runner records `budget.max_tokens` and `budget.max_seconds` in the plan.
The downstream council execution is responsible for enforcing those caps.

## Dedup window

Dedup looks up the deterministic `plan_hash`. If the toolbox policy is
`cached` and the existing plan is still inside `dedup.window_seconds`, the
runner returns that cached plan instead of writing a fresh one.

## Graph-blast expansion

When callers provide a graph edge map, `graph-blast` expands changed files by
one hop. Without a graph map, graph-blast falls back to the changed set so the
CLI remains deterministic and cheap.

## Related

- [Hooks & triggers](hooks.md) — how a plan gets executed.
- [Verdicts & guardrails](verdicts.md) — what the council leaves behind.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall