coordination-bridge
HTTP fallback bridge for coordinator when MCP transport is unavailable
Skill by jankneumann
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jankneumann-coordination-bridge
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 2
api.github.com· found in codecodeload.github.com· found in install command
Files it touches
~/.claude/skills/coordination-bridge- Your home directory (~)
What's inside
- Skill name
coordination-bridge- Description
- HTTP fallback bridge for coordinator when MCP transport is unavailable
- License
- MIT
- Instructions
- 129 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (14)
- SKILL.md
- __init__.py · scripts/_generated/
- features_models.py · scripts/_generated/
- features_operations.py · scripts/_generated/
- check_coordinator.py · scripts/
- coordination_bridge.py · scripts/
- generate_bindings.py · scripts/
- github_issues.py · scripts/
- routing_fallback.py · scripts/
- test_code_search_capability.py · scripts/tests/
- test_coordination_bridge.py · scripts/tests/
- test_feature_registry_helpers.py · scripts/tests/
- test_generated_bindings.py · scripts/tests/
- test_github_issues.py · scripts/tests/
SKILL.md (first lines)
# Coordination Bridge Infrastructure Skill Non-user-invocable infrastructure skill that provides HTTP fallback for the coordinator when MCP transport is unavailable. ## Scripts ### `<skill-base-dir>/scripts/coordination_bridge.py` Detects coordinator availability and provides HTTP-based fallback operations. **Usage**: ```bash python3 "<skill-base-dir>/scripts/coordination_bridge.py" <command> [args] ``` **Commands**: | Command | Arguments | Description | |---------|-----------|-------------| | `detect` | | Check coordinator availability, output JSON status | | `try_handoff_read` | `[--agent-name NAME] [--limit N]` | Read latest handoff (HTTP fallback) | | `try_handoff_write` | `--summary TEXT [--completed JSON] [--next-steps JSON]` | Write handoff document | | `try_recall` | `[--tags TAG,...] [--limit N]` | Recall memories by tags | | `try_remember` | `--event-type TYPE --summary TEXT [--tags TAG,...]` | Store a memory | **Stdout** (detect): JSON with `COORDINATOR_AVAILABLE`, transport, capabilities **Exit codes**: 0 = success, 1 = coordinator unavailable or error ## Feature registry helpers Five helpers cover every operation in the feature-registry contract (`openspec/contracts/agent-coordinator/openapi/features.yaml`). Each resolves its method and path from the generated `OPERATIONS` table, needs `CAN_FEATURE_REGISTRY` (probed with `GET /features/active`), and returns the bridge's uniform envelope: `ok` (contract-typed body in `data`), `skipped` (`coordinator_unavailable`, `capability_unavailable`, `coordinator_unreachable`, `unauthorized`, `forbidden`), or `error`. None of them raise. | Helper | operationId | `data` on `ok` | |--------|-------------|----------------| | `try_register_feature(*, feature_id, resource_claims, title=None, agent_id=None, branch_name=None, merge_priority=5, metadata=None)` | `registerFeature` | `FeatureRegisterResult` | | `try_deregister_feature(*, feature_id, status="completed")` | `deregisterFeature` | `FeatureDeregisterResult` | | `try_get_feature(*, feature_id)` | `getFeature` | `FeatureDetail` | | `try_list_active_features()` | `listActiveFeatures` | `ActiveFeaturesEnvelope` | | `try_analyze_feature_conflicts(*, candidate_feature_id, candidate_claims)` | `analyzeFeatureConflicts` | `ConflictReport` | All also accept `http_url=None, api_key=None`. `try_get_feature` URL-encodes the id into the path; an unknown id (404) comes back as a non-`ok` envelope. ## Contract-generated bindings `scripts/_generated/` is generated by `scripts/generate_bindings.py` from `openspec/contracts/` only (never from the running app's `app.openapi()`): - `features_models.py` — `TypedDict` models from pinned `datamodel-code-generator==0.83.0`. They use Python 3.11+ typing, so the bridge imports them **only under `if TYPE_CHECKING:`**. - `features_operations.py` — `OPERATIONS`: `operationId` → `Operation(method, path, path_params, requires_api_key, request_model, response_model)`. Imported at runtime, so it is **standard-library only and valid on Python 3.9**: skills run the bridge with bare `python3`, no venv. Do not edit `_generated/` by hand. The generator is a source-repository tool (it needs `openspec/contracts/` and the skills venv from `cd skills && uv sync --all-extras`). After changing a contract, regenerate from the repo root: ```bash skills/.venv/bin/python skills/coordination-bridge/scripts/generate_bindings.py # write (source-contribution-only) skills/.venv/bin/python skills/coordination-bridge/scripts/generate_bindings.py --check # CI gate (source-contribution-only) ``` `--check` writes nothing and exits non-zero naming each stale file and the regeneration command. Output is deterministic (no timestamps or absolute paths). To bind another contract, add a `(contract path, module prefix)` row to `CONTRACTS` in the generator. Re-running the skills installer refreshes the runtime copies under `.claude/skills/` and `.agents/skills/` with `_generated/`. ## Issue backend (issue #429) `try_issue_*` defaults to the coordinator HTTP API. Coordinator writes currently return success with a generated UUID and then vanish from every subsequent read, so the durable interim store is GitHub Issues in this repository. Opt in: ``` COORDINATION_ISSUES_BACKEND=github GITHUB_TOKEN=... # or GH_TOKEN / GITHUB_PAT COORDINATION_GITHUB_REPO=owner/repo # optional; GITHUB_REPOSITORY is also read ``` `COORDINATION_ISSUES_BACKEND=github` is required in GitHub Actions (where `GITHUB_TOKEN` and `GITHUB_REPOSITORY` are always set) so CI does not silently retarget onto live Issues. A failed GitHub write is a non-2xx that the bridge surfaces; it never reports `success: true` for a discarded record. `depends_on` is stored in the issue body (metadata comment + task list). Callers (`seed_tasks_from_md.py`, the status renderer) are unchanged. ## Work-Queue Truth / Projection Contract The queue helpers this skill exposes (`try_get_work` → `/work/claim`, `try_complete_work`, and the submit path) are a **distribution/claim mechanism only**. They are NOT a source of execution truth. **Contract**: `openspec/changes/<change-id>/loop-state.json` (schema: `LoopState` in `skills/autopilot/scripts/autopilot.py`) is the **authoritative execution state** — the source of truth for a run's current phase, iteration, and package status. The coordinator work queue is a **derived projection** whose entries are always re-derivable from loop-state. Truth flows loop-state → queue, **never** queue → loop-state. A `try_get_work` / `/work/claim` result is a work item to execute; it is never the record of what phase a run is in. No skill may read authoritative phase/loop-state from the work queue. This is the same asymmetry `coordinator-task-status-renderer` applies to the `tasks.md` checkboxes (truth) vs. the rendered coordinator status block (informational projection). See the full contract — idempotent submission keyed by
From jankneumann/agentic-coding-tools, MIT.
More from jankneumann/agentic-coding-tools
- 0.611score
bug-scrub
jankneumann
Comprehensive project health diagnostic — collects signals from CI tools, reports, deferred work, code markers, and open GitHub issues
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
autopilot-roadmap
jankneumann
Execute roadmap items iteratively with policy-aware vendor routing and learning feedback
SkillAFreshness: A★ 4Claude Code +9 - 0.605score
bao-vault
jankneumann
OpenBao/Vault credential seeding and management scripts
SkillAFreshness: A★ 4Claude Code +9 - 0.599score
autopilot
jankneumann
Orchestrate the full plan-review-implement-validate-PR lifecycle with multi-vendor review convergence
SkillAFreshness: A★ 4Claude Code +9 - 0.571score
codebase-atlas
jankneumann
Render the architecture graph as a single self-contained interactive HTML page — foldable structure tree, animated dependency graph, and cross-connection…
SkillBFreshness: B★ 4Claude Code +9 - 0.571score
audit-choices
jankneumann
Independent, read-only audit of implementation-time decisions made where the spec was silent, producing a schema-valid choices ledger
SkillBFreshness: B★ 4Claude Code +9 - 0.571score
collect-transcripts
jankneumann
Ingest raw session transcripts from coding-agent harnesses via vendor-specific adapters, normalize to a common event schema, triage for struggle signals, and…
SkillBFreshness: B★ 4Claude Code +9 - 0.568score
coordinator-task-status-renderer
jankneumann
Render and seed coordinator-owned task status block in OpenSpec tasks.md
SkillBFreshness: B★ 4Claude Code +9 - 0.568score
archive-roadmap
jankneumann
Archive a completed roadmap workspace to openspec/roadmaps/archive/<date>-<id>/
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
agent-ergonomics
jankneumann
Refine a system design or plan to be maximally agent-intuitive, agent-ergonomic, and agent-accretive — grounded in simulated agent journeys and real friction…
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
debugging-and-error-recovery
jankneumann
Guides systematic root-cause debugging with the Stop-the-Line rule and a reproduce → localize → reduce → fix → guard → verify triage checklist.
SkillBFreshness: B★ 4Claude Code +9 - 0.565score
context-engineering
jankneumann
Curates the right context for an agent at the right time.
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 129
- Last commit (this folder)
- Oct 9, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jankneumann
- 0.611score
bug-scrub
jankneumann
Comprehensive project health diagnostic — collects signals from CI tools, reports, deferred work, code markers, and open GitHub issues
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
autopilot-roadmap
jankneumann
Execute roadmap items iteratively with policy-aware vendor routing and learning feedback
SkillAFreshness: A★ 4Claude Code +9 - 0.605score
bao-vault
jankneumann
OpenBao/Vault credential seeding and management scripts
SkillAFreshness: A★ 4Claude Code +9 - 0.599score
autopilot
jankneumann
Orchestrate the full plan-review-implement-validate-PR lifecycle with multi-vendor review convergence
SkillAFreshness: A★ 4Claude Code +9 - 0.571score
audit-choices
jankneumann
Independent, read-only audit of implementation-time decisions made where the spec was silent, producing a schema-valid choices ledger
SkillBFreshness: B★ 4Claude Code +9 - 0.571score
codebase-atlas
jankneumann
Render the architecture graph as a single self-contained interactive HTML page — foldable structure tree, animated dependency graph, and cross-connection…
SkillBFreshness: B★ 4Claude Code +9
Cite this page
coordination-bridge skill. Agent Mart. https://agentmart.dev/skills/jankneumann-coordination-bridge (last updated 2026-10-24)