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-memorygit 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-memory)<a href="https://agentmods.dev/skills/mazen160/backlog/backlog-memory"><img src="https://agentmods.dev/badge/skills/mazen160/backlog/backlog-memory/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-memory"><img src="https://agentmods.dev/badge/skills/mazen160/backlog/backlog-memory.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 | $0.00083 | $0.01417 |
| Opus 5.5 | $0.00033 | $0.00567 |
| Sonnet 5.5 | $0.00017 | $0.00283 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
backlog-memory 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
backlog-memory
Two jobs, one skill:
- learn — read everything in a project (tasks, plans, docs, memory) into the current session. Read-only.
- store — synthesize the project's state into persistent memory entries, grouped by theme, so future sessions load context instantly.
Invocation
/backlog-memory— auto-pick the mode (see below), default project./backlog-memory <alias>— auto-pick the mode for that project./backlog-memory learn [alias]— force learn./backlog-memory store [alias]— force store.
Choosing the mode (when none is given)
An explicit learn / store always wins. Otherwise decide:
- Start of a fresh session / orienting — you've just started, little or no project context is loaded, the user wants to get up to speed → run learn.
- Work has been done this session — tasks were created, moved, or closed; plans or comments were added; decisions were made; the project state changed → run store to refresh the persisted summaries.
- Ambiguous / you can't tell — ask the user before doing anything: "Should I learn (load this project's context) or store (persist a fresh memory snapshot)?"
When you're unsure whether work has happened, check recent activity and use your judgment:
backlog activity --project <alias> --limit 20 --json --profile default
Recent writes by the current actor in this session lean toward store; a quiet log at the start of a session leans toward learn.
Resolve the project
backlog project list --json --profile default
Use the provided alias, or pick the project the user is actively working in. If it's genuinely unclear which project, ask.
Mode: learn (read into context)
The read phase — no writes.
1. Read everything in parallel
# Memory entries (decisions, architecture, context notes)
backlog memory list --project <alias> --json --profile default
# Docs list
backlog doc list --project <alias> --json --profile default
# Open tasks (todo + doing)
backlog task list --project <alias> --status todo --json --profile default
backlog task list --project <alias> --status doing --json --profile default
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 · 168 lines · 0 tokens per session scan A 1a1b5df28944
backlog-memory is a skill published in the GitHub repository mazen160/backlog (17 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 1,417 once invoked, about $0.0003 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.
rem-page-org
What an organisation's page in the notebook is made of — the fixed sections, when a company earns a page at all instead of staying a field on a person's, and the rules that keep it from becoming a second copy of everyone who works there. Composed into every stage that writes one.
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.
rem-project-sessions
Write or update one project page from the owner's messages and a bounded packet of local project evidence.
mnemosyne
Use when curating WrongStack SAGE memory: run deterministic hygiene and anchor verification first, then review contradictions, drift, and noise; file destructive outcomes as review proposals instead of deleting directly.
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.