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 nulab/bee --skill backlog-notationgit clone --depth 1 https://github.com/nulab/beeWrote 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/nulab/bee/backlog-notation)<a href="https://agentmods.dev/skills/nulab/bee/backlog-notation"><img src="https://agentmods.dev/badge/skills/nulab/bee/backlog-notation/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/nulab/bee/backlog-notation"><img src="https://agentmods.dev/badge/skills/nulab/bee/backlog-notation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00201 | $0.01478 |
| Opus 5.5 | $0.00080 | $0.00591 |
| Sonnet 5.5 | $0.00040 | $0.00296 |
| Haiku 4.5 | $0.00020 | $0.00148 |
Grade A, and why
backlog-notation scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -F "[email protected]" https://xxx.backlog.com/api/v2/... How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog-notation
Backlog notation (Backlog記法) syntax reference.
When this applies
Every Backlog project is set to one text formatting rule: Markdown (the default for new projects) or Backlog notation. This reference covers Backlog notation only. It is not a Backlog-wide standard, and it does not apply to Markdown projects — in those, write plain Markdown and ignore everything below.
Backlog renders text strictly by the project's rule: Backlog notation posted to a Markdown project (or vice versa) is not converted — it shows up as literal characters like ''bold'' or **bold**. Determine the rule like this:
-
The user or project instructions (AGENTS.md, CLAUDE.md) already state the rule — the usual case. Follow what is stated; do not spend an API call re-verifying it.
-
The rule is not stated anywhere — check it once before posting:
bee project view -p PROJECT_KEY --json textFormattingRule # {"textFormattingRule":"backlog"} -> use this reference # {"textFormattingRule":"markdown"} -> use Markdown insteadIf you cannot run bee (e.g. this skill is installed without it), fetch
/api/v2/projects/PROJECT_KEYfrom the Backlog API and readtextFormattingRule, or ask the user.
Backlog notation is not Markdown — never mix the two syntaxes in one text.
Quick Reference
| Feature | Syntax |
|---|---|
| Heading | * H1 / ** H2 / *** H3 / **** H4 |
| Bold | ''text'' |
| Italic | '''text''' |
| Strikethrough | %%text%% |
| Color | &color(red) { text } |
| Color + background | &color(#fff, #333) { text } |
| Bullet list | - item (nest with --) |
| Numbered list | + item (nest with ++) |
| Checklist | - [ ] todo / - [x] done (issue descriptions only) |
| Link | [[https://example.com]] |
| Labeled link | [[label>https://example.com]] |
| Issue link | PROJECT-123 (auto-linked) |
| Quote | > text or {quote}...{/quote} |
| Code block | {code}...{/code} |
| Code (lang) | {code:java}...{/code} |
| Image | #image(URL or filename) |
| Thumbnail | #thumbnail(URL or filename) (< 200KB) |
| Table of contents | #contents |
| Line break | &br; |
| Escape | \ before special characters |
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 · 117 lines · 201 tokens per session scan A 1e5cb1372567
backlog-notation is a skill published in the GitHub repository nulab/bee (97 stars, last pushed 7d ago), licensed MIT. It adds 201 tokens to every session and 1,478 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
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…