Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/romiluz13/cc-teams/router-contractnpx skills add romiluz13/cc-teams --skill router-contractgit clone --depth 1 https://github.com/romiluz13/cc-teamsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/romiluz13/cc-teams/router-contract)<a href="https://agentmods.dev/skills/romiluz13/cc-teams/router-contract"><img src="https://agentmods.dev/badge/skills/romiluz13/cc-teams/router-contract.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.10051 |
| Opus 5 | $0.00016 | $0.05025 |
| Sonnet 5 | $0.00006 | $0.02010 |
| Haiku 4.5 | $0.00003 | $0.01005 |
Grade A, and why
router-contract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 804 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Router Contract (CC-Teams)
Purpose
The Router Contract is a machine-readable YAML block output by every teammate at the end of their work. The lead uses it to:
- Validate teammate output quality
- Decide whether to proceed or block
- Collect memory notes for persistence
- Resolve conflicts between teammates
Contract Format (REQUIRED)
Every teammate MUST include this section at the end of their output:
### Router Contract (MACHINE-READABLE)
```yaml
CONTRACT_VERSION: "2.5"
STATUS: [value from agent-specific list below]
CONFIDENCE: [0-100]
CRITICAL_ISSUES: [count]
HIGH_ISSUES: [count]
BLOCKING: [true|false]
REQUIRES_REMEDIATION: [true|false]
REMEDIATION_REASON: [null or description of what needs fixing]
SPEC_COMPLIANCE: [PASS|FAIL|N/A]
TRACEABILITY_IMPACT: [none|risk_detected|conflict_detected] # reviewers + hunter + live-reviewer
REQUIREMENTS_AT_RISK: [list or empty] # reviewers + hunter + live-reviewer
ACCEPTANCE_CRITERIA_AT_RISK: [list or empty] # reviewers + hunter + live-reviewer
DECISION_DEPENDENCIES_AT_RISK: [list or empty] # reviewers + hunter + live-reviewer
# v2.5 additions (agent-specific — include only for relevant roles):
PHASE_ID: "[phase id or ad-hoc-scope]" # builder family
PHASE_STATUS: [completed|partial|blocked] # builder family
PHASE_EXIT_READY: [true|false] # builder family
CHECKPOINT_TYPE: [none|human_verify|decision|human_action] # builder family
PROOF_STATUS: [passed|gaps_found|human_needed] # builder family + verifier
INPUTS: [list or empty] # builder family
EXPECTED_ARTIFACTS: [list or empty] # builder family
REQUIREMENT_IDS_IN_SCOPE: [list or empty] # builder family
ACCEPTANCE_CRITERIA_IN_SCOPE: [list or empty] # builder family
APPROVED_DECISION_DEPENDENCIES: [list or empty] # builder family
REQUIREMENTS_SATISFIED: [list or empty] # builder family
ACCEPTANCE_CRITERIA_SATISFIED: [list or empty] # builder family
DECISION_DEPENDENCIES_SATISFIED: [list or empty] # builder family
TDD_RED_EXIT: [1|null] # builder family
TDD_GREEN_EXIT: [0|null] # builder family
PHASE_GATE_RESULT: [PASS|FAIL|N/A] # builder family
PHASE_GATE_CMD: ["gate command or N/A"] # builder family
SCENARIOS: # builder family
- name: "[scenario name]"
given: "[state]"
when: "[action]"
then: "[result]"
command: "[exact command]"
expected: "[expected result]"
actual: "[actual result]"
exit_code: [code]
status: [PASS|FAIL|BLOCKED]
ASSUMPTIONS: [list or empty] # builder family
DECISIONS: [list or empty] # builder family
BLOCKED_ITEMS: [list or empty] # builder family
SKIPPED_ITEMS: [list or empty] # builder family
SCOPE_INCREASES: [list or empty] # builder family
PLAN_MODE: [direct|execution_plan|decision_rfc] # planner only
VERIFICATION_RIGOR: [standard|critical_path] # planner only
OPEN_DECISIONS: [list or empty] # planner only
RECOMMENDED_DEFAULTS: [list or empty] # planner only
CONTRADICTIONS_FOUND: [count] # planner only
REQUIREMENT_PHASE_COVERAGE: [complete|gaps_found] # planner only
ACCEPTANCE_PROOF_COVERAGE: [complete|gaps_found] # planner only
FINDING_BUCKETS: # plan-gap-reviewer only
repo_mismatches: [count]
missing_surfaces: [count]
execution_order_issues: [count]
hidden_assumptions: [count]
under_scoped_integrations: [count]
open_decisions_presented_as_settled: [count]
requirement_conflicts: [count]
traceability_gaps: [count]
REPLAN_NEEDED: [true|false] # plan-gap-reviewer only
REPLAN_REASON: [reason or "None"] # plan-gap-reviewer only
DEPENDENCY_AUDIT: [PASS|WARN|FAIL|SKIPPED] # verifier + security-reviewer
DEPENDENCY_AUDIT_DETAIL: ["detail or N/A"] # verifier only
SCENARIOS_FAILED: [count] # verifier only
PROOF_RECONCILIATION: # verifier only
truths: [verified|missing|human_needed]
artifacts: [verified|missing|human_needed]
wiring: [verified|missing|human_needed]
SCENARIO_EVIDENCE: # verifier only
- name: "[scenario]"
command: "[command]"
expected: "[expected]"
actual: "[actual]"
exit: [code]
result: [PASS|FAIL|BLOCKED]
TRACEABILITY_STATUS: [verified|gaps_found|human_needed] # verifier only
REQUIREMENTS_VERIFIED: [list or empty] # verifier only
ACCEPTANCE_CRITERIA_VERIFIED: [list or empty] # verifier only
DECISION_DEPENDENCIES_CHECKED: [list or empty] # verifier only
TRACEABILITY_GAPS: [list or empty] # verifier only
STATE_DELTA:
what_changed: [list or empty]
remains_open: [list or empty]
should_stay_closed: [list or empty]
next_trigger: "[next required action or None]"
TIMESTAMP: [ISO 8601 timestamp]
AGENT_ID: [teammate name, e.g., "investigator-1"]
FILES_MODIFIED: [list of files changed, or empty]
CLAIMED_ARTIFACTS: [durable files claimed as created/updated by this teammate, or empty]
EVIDENCE_COMMANDS: ["command => exit <code>", "..."]
DEVIATIONS_FROM_PLAN: [null or description of what changed from plan]
MEMORY_NOTES:
learnings: ["insight 1", "insight 2"]
patterns: ["pattern or gotcha discovered"]
verification: ["evidence of what was verified"]
```
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 804 lines · 32 tokens per session scan A a3f86df54b7c
router-contract is a skill published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 10,051 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…