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 martineserios/thebrana --skill backloggit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/backlog)<a href="https://agentmods.dev/skills/martineserios/thebrana/backlog"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/backlog/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/martineserios/thebrana/backlog"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/backlog.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 | $0.00030 | $0.04079 |
| Opus 5.5 | $0.00012 | $0.01632 |
| Sonnet 5.5 | $0.00006 | $0.00816 |
| Haiku 4.5 | $0.00003 | $0.00408 |
Grade A, and why
backlog 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog
Manage the project backlog — plan, track, and navigate work across phases, milestones, and epics. Natural language is the primary interface; these commands are shortcuts for complex operations.
When to use
When explicitly managing the backlog: planning phases, viewing roadmaps, restructuring work. Daily task interaction happens through natural language guided by the task-convention rule — no skill invocation needed.
CLI Integration — MANDATORY
NEVER read or write tasks.json directly.
Prefer MCP tools (brana server) when available — structured JSON, 65% fewer tokens:
Initiative Model (v3)
Epics are hierarchy nodes, not a field (ADR-065). An epic is a top-level task with type: "epic" whose subject is the epic slug (e.g. "cc-alignment"). A task belongs to an epic through its parent chain — its nearest type: "epic" ancestor (walk helper: ../_shared/epic-ancestor-walk.md).
Retired — flat
epicfield. The pre-v3 flatepicstring field is gone and its set/add write paths are sealed (t-2310):backlog_set(field: "epic")andbrana backlog set <id> epic <slug>are hard-rejected withunknown field: epic, andbrana backlog add --epicis a warned no-op. Never set or create the field. Epic membership is written by settingparentto an epic node's id.Mid-migration caveat (t-2698): the ADR-065 backfill (promote old epic slugs to nodes, re-parent tasks) has only run in some projects (e.g. thebrana). In a project whose tasks.json has no
type: "epic"nodes yet, first create the epic node (brana backlog add --subject "<slug>" --type epic), then parent tasks to it — or, if restructuring isn't warranted yet, tag tasksepic:<slug>as the interim marker (see below). Never resurrect the flat field.
Lightweight epic tag — epic:<slug>. The namespaced tag epic:<slug> (e.g. epic:cc-alignment) is the sanctioned lightweight epic marker: a memorable grouping label for tasks of any size. Use it (a) as the interim marker in un-migrated projects (caveat above), and (b) as an extra cross-cutting handle anywhere a greppable epic label helps. It reads/writes like any tag — backlog_set(field: "tags", value: "+epic:cc-alignment") / brana backlog set <id> tags +epic:cc-alignment — and filters like any tag: backlog_query(tag: "epic:cc-alignment") / brana backlog query --tag epic:cc-alignment. The namespace prefix keeps it from colliding with ordinary tags. Limits: tags do NOT feed focus, the --epic filters, or branch naming — where epic nodes exist, the parent chain stays authoritative; parent to the node first and add the tag only when the extra label earns its keep.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -3 lines b17b7fe9bcb2
- 1mo ago First seen · 213 lines · 30 tokens per session scan A 7af90ff0096b
backlog is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 4,079 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
hs-plan
Turns an agreed Decision Brief or clear direction into a grounded implementation-ready plan with independently verifiable tasks and acceptance criteria. Use after hs-brainstorm or when the implementation direction is already settled. It does not choose approaches or write implementation code. With --gh, it publishes…
foreman
The one entrance to Foreman, which keeps a project's plan and task history. Say what you want in plain language and this routes it to one of the six things Foreman does to a project: add work, show status, correct work, check the roadmap, pick work, or reconcile and pick. It owns no flow of its own. Use for Foreman or…
github-issue-triage
A GitHub issue organiser for open problems and requests in a software project. GitHub is a service where teams store code and track issues.
tasknotes
This skill should be used when the user asks to 'create a task', 'add a TODO', 'plan a sprint', 'organize tasks', 'track time', 'setup Kanban', 'create task from code', 'sync tasks with sprint', 'pomodoro session', 'start pomodoro', 'time estimate', or mentions TaskNotes, task management, or project planning in…
sdd-implement
Execute one or more tasks from the SDD task list. Use when the user says 'implement task', 'execute task', 'build task', 'do TASK-001', 'next task', 'start implementing', or wants to work on specific tasks. Reads only task blocks and their listed files. Auto-batches small tasks when possible.
sw-status
Shows current Specwright state for this worktree, the attached work, repo-wide active works, gate results, and lock status. Supports --reset, --cleanup, and --repair {unitId}.