A local project record system built from Markdown files, with tools for storing work, decisions, project knowledge, and durable memory. It can be accessed through a command line or an agent tool connection.

Use it to recall project information, write threaded architecture decisions, maintain work records, and define project-specific information structures.

It keeps important project context available across sessions instead of leaving decisions and knowledge only in a conversation. It also helps retrieve authoritative records and corrections.

How gkoreli/backlog-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to gkoreli/backlog-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gkoreli/backlog-mcp/main/.agents/skills/backlog/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/gkoreli/backlog-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gkoreli/backlog-mcp/backlog/github.svg)](https://agentmods.dev/skills/gkoreli/backlog-mcp/backlog)

Your own site

<a href="https://agentmods.dev/skills/gkoreli/backlog-mcp/backlog"><img src="https://agentmods.dev/badge/skills/gkoreli/backlog-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gkoreli/backlog-mcp/backlog"><img src="https://agentmods.dev/badge/skills/gkoreli/backlog-mcp/backlog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.00655
Opus 5.5	$0.00019	$0.00262
Sonnet 5.5	$0.00009	$0.00131
Haiku 4.5	$0.00005	$0.00065

Measured 28d ago against content hash 6479d8ff69a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 28d 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.

.agents/skills/backlog/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use backlog-mcp

Backlog is a local-first Markdown corpus; indexes and the viewer are projections. Use the available MCP connection or CLI; preserve the project's document conventions. This folder is portable: copy it with its references into another project's skills directory.

Select the home and contract

Identify the intended project root and select its home before reading or writing.
CLI: inspect backlog --help; use --home project --project-root /absolute/repo.
MCP: expand the selected tool's full schema; use its home fields or connection selection.
Use content for the Markdown body; discovery summaries are not input contracts.
Read CLI and MCP for setup, selection, invocation, and receipts.

Orient, retrieve, and expand

Wake once at session start: backlog_wakeup or backlog wakeup.
After context loss, resume from the durable work record; use a known operation when available.
Recall once per topic when learned knowledge matters; inspect age, source, and correction lineage.
Search to locate current documents; use list for filters and get for authoritative detail.
Expand selected entities with get's context option, then hydrate only relevant neighbor stubs.
Recall and search have distinct semantics even when they share candidate retrieval.
Current user direction, accepted project decisions, and verified contracts outweigh stale memory.

Make meaningful changes

Discover the substrate's declared action and read its inputs before invoking it.
Keep task progress, architectural decisions, and remembered lessons in their owning records.
Use explicit memory correction (supersedes or state_key), preserving prior-holder lineage.
Forget retracts knowledge; deletion permanently removes records; expired-memory GC removes history.
Preserve Markdown; inspect committed receipts, warnings, and home/path provenance before retrying.
Read Memory when capturing, correcting, retracting, or consolidating knowledge.
Read CLI and MCP before managed writes: current adapters have gaps.

Read the full file on GitHub · 51 lines

Files

What ships with it

6 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.

Changes

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.

28d ago First seen · 51 lines · 47 tokens per session scan A 6479d8ff69a1

Subscribe to this mod's changes

backlog is a skill published in the GitHub repository gkoreli/backlog-mcp (5 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 655 once invoked, about $0.0002 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 2026-10-09.

LLM Memory and context Project management ai anthropic claude mcp model-context-protocol

backlog next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
backloggkoreli/backlog-mcp	Skill	5	29d ago	MIT	A	47	Claude Code, Codex
unified-memoryaffaan-m/ECC	Skill	298k	4d ago	MIT	A	60	Claude Code, Codex
llm-wikiNousResearch/hermes-agent	Skill	261k	yesterday	MIT	B	19	Claude Code, Codex
qmdNousResearch/hermes-agent	Skill	261k	yesterday	MIT	B	14	Claude Code, Codex
strategic-compactaffaan-m/ECC	Skill	298k	4d ago	MIT	B	47	Claude Code, Codex
hermes-agentNousResearch/hermes-agent	Skill	261k	yesterday	MIT	C	18	Claude Code, Codex
caveman-compressJuliusBrussee/caveman	Skill	118k	yesterday	Apache-2.0	C	54	Claude Code

backlog-mcp: Skill for Claude Code