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 agentmods add skills/sammcj/agentic-coding/backlognpx skills add sammcj/agentic-coding --skill backloggit clone --depth 1 https://github.com/sammcj/agentic-codingWhat 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 | $0.00182 | $0.01440 |
| Opus 5 | $0.00091 | $0.00720 |
| Sonnet 5 | $0.00036 | $0.00288 |
| Haiku 4.5 | $0.00018 | $0.00144 |
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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog management
Capture single items to a project backlog, or list and triage an existing one. Detect the user's intent and run in either add mode (one item being filed) or review mode (looking at what's there). The two modes share destination detection.
Destination detection
Try in order; cache the result for any follow-up in the same flow:
gh repo viewsucceeds → use GitHub issues for that repo.- Else
docs/BACKLOG.mdexists → append for adds, read for reviews. - Else
docs/issues/directory exists → per-issue files (one.mdper issue, numbered prefix). - Else ask the user where to put it. Don't silently create files in the project root.
If the user invokes this skill in a directory with no obvious project (no git, no docs/), say so and ask before doing anything.
Add mode
The user has a single item to file. Goal: lower ceremony than typing the issue themselves. If it's heavier than that, they'll stop using the skill.
-
Dupe check. Search existing items for keyword overlap (
gh issue list --search "<keywords>"or grep the local file). If a near-match exists, surface it and ask whether to update that one or file new. This is the cheapest defence against ending up with three issues for the same thing. -
Enhance proportional to input. A one-liner from the user warrants 2-3 short context bullets drawn from CLAUDE.md and the current project state (technical caveats, related modules, open questions). If the user already wrote a paragraph or more, file it as-is. Don't restructure their words. The point of enhancement is to capture context they didn't bother to type, not to dress up what they did type.
-
One clarifying question max, and only when scope or category (bug vs enhancement) is genuinely ambiguous. If you can guess from context, guess.
-
File and return the URL or path. No trailing summary; the URL is the receipt.
Labels
GitHub: pick from gh label list. Don't invent new labels without asking. Projects often have label conventions wired into filters, project boards, or release automation, and an invented label is invisible to those.
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.
- yesterday First seen · 77 lines · 182 tokens per session scan A 783c9c88415f
backlog is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 7d ago), licensed Apache-2.0. It adds 182 tokens to every session and 1,440 once invoked, about $0.0009 per session on Opus 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
docs-planner
Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…
local-browser
Drive the user's real, authenticated Chrome from an agentproto-connected client. Use when a task needs the user's live cookies, sessions, or extensions (Gmail, LinkedIn, GitHub, ad managers, internal tools) rather than a fresh anonymous browser.
ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.