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 mazen160/backlog --skill backlog-goalgit clone --depth 1 https://github.com/mazen160/backlogWrote 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/mazen160/backlog/backlog-goal)<a href="https://agentmods.dev/skills/mazen160/backlog/backlog-goal"><img src="https://agentmods.dev/badge/skills/mazen160/backlog/backlog-goal/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/mazen160/backlog/backlog-goal"><img src="https://agentmods.dev/badge/skills/mazen160/backlog/backlog-goal.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 | $0.00167 | $0.12947 |
| Opus 5.5 | $0.00067 | $0.05179 |
| Sonnet 5.5 | $0.00033 | $0.02589 |
| Haiku 4.5 | $0.00017 | $0.01295 |
Grade A, and why
backlog-goal 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 — 1,025 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog-goal
End-to-end goal pursuit, recorded in a backlog workspace. Every step the agent takes is observable through the backlog CLI: tasks for the work, plans for the how, structured-receipt comments for the audit trail, memory for the brief, and a Judge sub-agent that gates every checkpoint.
Requires: the backlog skill
This skill is a thin orchestrator on top of the backlog CLI. Before doing anything in PREP or RUN, load the backlog skill (skills/backlog/skill.md in this repo, also exposed as the backlog skill in the user's available-skills list). That skill is the canonical reference for:
- every CLI flag (
--profile,--as,--json,--db,--quiet) - the full surface for
project,task,plan,comment,label,memory,doc,attachment,import-findings,export,activity - ID formats (
TASK-N, bare integer, full ULID) - JSON response shapes for parsing
- enum values for
type,status,priority,actor.kind - DB resolution order and profile semantics
- MCP tool names and signatures (if the goal is being executed via MCP rather than the CLI)
If you find yourself guessing a flag name or a JSON field shape, stop and re-read skills/backlog/skill.md. This skill (backlog-goal) assumes you already know how to drive the CLI; it does not re-document it. The "Quick command reference" section at the bottom is a cheat sheet, not a replacement for the full skill.
When operating in this repo, also respect the conventions noted in docs/CLAUDE/MEMORY.md: always pass --profile default (because go test can leave an e2etest profile registered), always attribute writes to --as ai:claude-opus-4-7 (or the current model's exact ID), and remember the binary is ./backlog at the repo root after make build.
Why two modes
The single most common failure of a "set a goal" loop is to skip discovery and start coding. This skill enforces a hard wall: PREP asks questions, classifies the goal, and seeds the board, then STOPS. RUN executes the board the user just confirmed. The user must explicitly invoke RUN — prep never starts work. This invocation boundary is borrowed from GoalBuddy and is non-negotiable: the questions are the work.
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 · 1,025 lines · 167 tokens per session scan A 756772eca2e7
backlog-goal is a skill published in the GitHub repository mazen160/backlog (17 stars, last pushed 3mo ago), licensed MIT. It adds 167 tokens to every session and 12,947 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
starting-a-new-project
Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.
importing-a-codebase
Use when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
asking-user-questions
Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.