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 skills add Jamie-BitFlight/claude_skills --skill backend-resolutiongit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/backend-resolution)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/backend-resolution"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/backend-resolution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/backend-resolution"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/backend-resolution.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.00976 |
| Opus 5.5 | $0.00022 | $0.00390 |
| Sonnet 5.5 | $0.00011 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
backend-resolution 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Resolution
A dh project has exactly one configured backlog backend. Everything backlog-shaped — work items, grooming, plans, task state, artifact manifests, artifact content — belongs to that one backend. Your job is to find out which one it is before you act, and to act consistently with the answer.
The chain
Resolution runs in this order, first hit wins:
- The
BACKLOG_BACKENDenvironment variable, when set to a non-empty value. backlog.backendin.dh/config.yaml.backend.namein the same file — the global fallback, checked only when the subsystem key above is absent. Steps 2 and 3 are applied per config file, in the config search order, so a nearer file's global key wins over a farther file's subsystem key.- The
.beads/dh-backendmarker file. Its presence, and nothing else, opts a project into the Beads backend. - Otherwise
github.
create_backend() in backlog_core/backend_protocol.py is the implementation; it delegates the
chain to DHConfig.get_backend(subsystem="backlog") in dh_config.py, and _auto_detect_beads()
implements step 4. docs/backend-providers.md under "One configured backend" is the canonical
description of the contract — read it when you need the storage model, per-backend capabilities,
or the cache and revision rules rather than the resolution procedure.
Do not re-derive this
Resolve the backend by reading the chain above and applying it in full, or by asking the harness for the answer. Do not write your own detection snippet. Two shapes have already shipped in agent prompts and both returned a confidently wrong answer:
- Stopping at the environment variable. A heuristic that reads
BACKLOG_BACKEND, then falls through to a default, never consults.dh/config.yaml. In a project that configures its backend there — the normal case, since the environment variable is the override, not the setting — it reports the default while the rest of the plugin uses the configured backend. - Testing for a
.beadsdirectory instead of the marker. Step 4 requires the file.beads/dh-backend. The directory alone is explicitly not sufficient: a project may keep a.beadsdirectory for other purposes without intending to use the Beads backlog backend. A heuristic that tests the directory reads such a project as Beads even when it configuresgithub.
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.
- 1mo ago First seen · 78 lines · 56 tokens per session scan A 08e75ff8b110
backend-resolution is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 976 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…