Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
.backlog - Skill - OpenSmartRoute
Skillv1.0.0
.backlog
`bl` / `backlog` is the **Go** client and the canonical one. The `backlog/` (Python) and `backlog_ts/` (TypeScript) trees exist **only as parity-test helpers** — they re-implement the same CLI surface
Imported from XertroV/backlog (.backlog/AGENTS.md). Install upstream with npx skills add XertroV/backlog --skill .backlog. Copyright stays with the author.
AGENTS.md
Agent workflow
Always use bl to create and modify backlog tasks.
Use bl --help before acting if you need command-level guidance.
Run bl howto to review workflow expectations.
Client implementations
bl / backlog is the Go client and the canonical one. The backlog/
(Python) and backlog_ts/ (TypeScript) trees exist only as parity-test
helpers — they re-implement the same CLI surface so cross-client parity
tests can verify behaviour against the Go reference. Don't pip install the
Python package or bun install/npm install the TS package in your dev
environment; they are not user-facing tools. If you need to run a parity
test locally, invoke the scripts directly (e.g. python backlog.py ... or
bun run backlog_ts/src/cli.ts ...) — the CI workflow does the same.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install .backlog and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
xertrov-backlog-backlog.ocm.jsonjson
{
"ocm": "1",
"id": "xertrov-backlog-backlog",
"kind": "skill",
"name": ".backlog",
"description": "`bl` / `backlog` is the **Go** client and the canonical one. The `backlog/` (Python) and `backlog_ts/` (TypeScript) trees exist **only as parity-test helpers** — they re-implement the same CLI surface so cross-client parity tests can verify behaviour against the Go reference. Don't `pip install` the Python package or `bun install`/`npm install` the TS package in your dev environment; they are not user-facing tools. If you need to run a parity test locally, invoke the scripts directly (e.g. `python backlog.py ...` or `bun run backlog_ts/src/cli.ts ...`) — the CI workflow does the same.",
"publisher": "XertroV",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"github-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"`bl` / `backlog` is the **Go** client and the canonical one. The `backlog/` (Python) and `backlog_ts/` (TypeScript) trees exist **only as parity-test helpers** — they re-implement the same CLI surface so cross-client parity tests can verify behaviour against the Go reference. Don't `pip install` the Python package or `bun install`/`npm install` the TS package in your dev environment; they are not user-facing tools. If you need to run a parity test locally, invoke the scripts directly (e.g. `python backlog.py ...` or `bun run backlog_ts/src/cli.ts ...`) — the CI workflow does the same."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-agents",
"repository": "https://github.com/XertroV/backlog",
"path": ".backlog/AGENTS.md",
"ref": "b50a9cf038cca6a9b6a1be1989d5a8ddf4cebef0",
"url": "https://github.com/XertroV/backlog/blob/b50a9cf038cca6a9b6a1be1989d5a8ddf4cebef0/.backlog/AGENTS.md",
"key": "XertroV/backlog/.backlog/AGENTS.md"
}
},
"instructions": "# AGENTS.md\n\n## Agent workflow\n\n- Always use `bl` to create and modify backlog tasks.\n- Use `bl --help` before acting if you need command-level guidance.\n- Run `bl howto` to review workflow expectations.\n\n## Client implementations\n\n`bl` / `backlog` is the **Go** client and the canonical one. The `backlog/`\n(Python) and `backlog_ts/` (TypeScript) trees exist **only as parity-test\nhelpers** — they re-implement the same CLI surface so cross-client parity\ntests can verify behaviour against the Go reference. Don't `pip install` the\nPython package or `bun install`/`npm install` the TS package in you",
"cost": {
"context_tokens": 205
}
}
Fetch it by URL: GET /api/v1/registry/xertrov-backlog-backlog/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
