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/ebizsoft/agentic-claude-code/issue-memorynpx skills add ebizsoft/agentic-claude-code --skill issue-memorygit clone --depth 1 https://github.com/ebizsoft/agentic-claude-codeWhat 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 | $0.00201 | $0.01890 |
| Opus 5 | $0.00101 | $0.00945 |
| Sonnet 5 | $0.00040 | $0.00378 |
| Haiku 4.5 | $0.00020 | $0.00189 |
Grade A, and why
issue-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 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
issue-memory — GitHub issues as durable agent memory
A stateless agent forgets everything between sessions. This pattern gives it a durable, GitHub-native memory that survives context resets and hands off cleanly between sessions and between agents: one pinned issue per repo, titled "Project log", that any agent reads first and updates last.
The skill is an installer + reference, not a runtime. It does not "run" during a work
session. It (a) seeds a repo with the labels, the pinned log, and a CLAUDE.md conventions
block (scripts/bootstrap.sh), and (b) documents the conventions so agents apply them.
The enforcement mechanism is the target repo's CLAUDE.md — that file is auto-loaded
every session, so the rituals below only actually happen if the conventions section lives
there. templates/claude-md-section.md is that section; bootstrap prints it to append.
What the Project log is (and is not)
One issue per repo, titled "Project log", pinned, labelled agent-context +
decision. It holds three things and nothing else:
- A numbered decision register — every decision that overrides the spec, handoff, or docs, recorded before or with the code that depends on it.
- A current-state summary — where the project is right now, at summary altitude.
- An open-decisions list — what is blocked on a human, cross-referencing
needs-decisionissues.
It is not a changelog and not a work tracker. See "Log altitude" below.
The two rituals
These live in the target repo's CLAUDE.md so every session inherits them.
- Session start: run
gh issue list --state openand read the pinned Project log issue before writing any code. That is the state of the world; specs and docs are older than it. - Session end: comment on every issue you touched with what is done and what is
half-finished, so the next session sees exactly where to resume. Close issues with
Closes #Nin commit messages — never by hand, so the close is tied to the commit that did the work.
What ships with it
3 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.
- yesterday First seen · 142 lines · 201 tokens per session scan A a2146220c169
issue-memory is a skill published in the GitHub repository ebizsoft/agentic-claude-code (2 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 1,890 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…