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 bamdadd/lintel --skill lintel-board-prioritisegit clone --depth 1 https://github.com/bamdadd/lintelWrote 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/bamdadd/lintel/lintel-board-prioritise)<a href="https://agentmods.dev/skills/bamdadd/lintel/lintel-board-prioritise"><img src="https://agentmods.dev/badge/skills/bamdadd/lintel/lintel-board-prioritise/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/bamdadd/lintel/lintel-board-prioritise"><img src="https://agentmods.dev/badge/skills/bamdadd/lintel/lintel-board-prioritise.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 | $0.00036 | $0.00918 |
| Opus 5.5 | $0.00014 | $0.00367 |
| Sonnet 5.5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
lintel-board-prioritise 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 2mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lintel-board-prioritise — Groom and Prioritise Board Work Items
Review all work items on the board, clean up completed/stale items, break down oversized tasks, and prioritise the backlog aligned with the Lintel vision.
Context: Lintel Vision
Lintel is the AI-human engineering platform — both measurement system and execution engine. Prioritisation should favour work that advances these pillars (in order):
- Event infrastructure — event store, bus, projections, subscriptions
- Collaboration & routing — teams, channels, integrations
- Guardrails & safety — cost limits, escalation, sandbox hardening
- Deployment & observability — deployments, incidents, feature flags
- Measurement & analytics — DORA metrics, agent accuracy, team velocity
- Continuous improvement — learning loops, automated remediation
Workflow Capacity Reference
A single feature_to_pr workflow run can handle work that fits in roughly one focused feature or bug fix — 11 stages: ingest → route → setup_workspace → research → plan → implement (up to 5 review cycles) → review → close. If a task requires multiple unrelated code changes across different packages, or touches more than ~3 files substantially, it should be broken down.
Steps
1. Fetch current state
Use MCP tools to gather data:
mcp__lintel__boards_list_boards— get all boards (needs a project_id; list projects first if needed)mcp__lintel__work-items_list_work_items— get all work items
Present a summary table of current work items grouped by status.
2. Groom — remove completed work
Identify work items with terminal statuses (merged, closed) — these are done. Delete them with mcp__lintel__work-items_remove_work_item.
Also identify failed items — ask the user whether to retry (move back to open) or delete.
Report what was cleaned up.
3. Assess scope — break down oversized tasks
For each remaining open work item, evaluate whether it can be completed in a single feature_to_pr run:
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.
- 2mo ago First seen · 85 lines · 36 tokens per session scan A 532cec3c33a2
lintel-board-prioritise is a skill published in the GitHub repository bamdadd/lintel (10 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 918 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.
07-epic
Produces or refines an outcome-based Epic for a product backlog. Use when the user wants to frame, review, resume, or persist an Epic. Not for Product Briefs, User Stories, or implementation.
09-defect
Produces or refines a backlog Defect from an observed product mismatch. Use when the user wants to report, assess, link, order, transition, or verify a defect. Not for incident response, debugging, or implementation.
os-workflow
A workflow guide for sending work from an AI Team OS project back into its task records. It explains how a lead agent and workflow agents record progress and important results.
ops-dora
CocoOps DORA metrics — computes four DORA-adapted delivery metrics from Snowflake task history and git log. Extends the longitudinal delivery thesis through the skill-native CocoOps thesis workflow. Invoked via $ops dora.
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.