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/gregmos/memoforge/continuenpx skills add gregmos/memoforge --skill continuegit clone --depth 1 https://github.com/gregmos/memoforgeWhat 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 | $0.00045 | $0.13372 |
| Opus 5 | $0.00023 | $0.06686 |
| Sonnet 5 | $0.00009 | $0.02674 |
| Haiku 4.5 | $0.00005 | $0.01337 |
Grade A, and why
continue 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 — 605 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memoforge / continue skill
You are the main session resuming an interrupted legal memo task. This is the explicit recovery path when automatic reentry on the memo skill did not pick up the previous state (closed tab, new session, long pause).
Note on phase references (B1b router refactor)
This skill cites the memo skill's procedures as "skills/memo/SKILL.md Phase N" / "memo Phase N step X". As of the B1b refactor, SKILL.md is a thin router; the full per-phase procedure prose now lives in skills/memo/references/phases/phase-<n>.md (mapped from current_phase by the dispatch table in SKILL.md §"Phase procedures"). So wherever this skill says "execute / mirror memo Phase N", read the matching references/phases/phase-<n>.md (e.g. Phase 1.5 → phase-1_5.md, Phase 2a/2b → phase-2a.md/phase-2b.md, Phase 9 → phase-9.md, Phase 11 → phase-11.md). Any "lines around N" citations are stale post-refactor — find the content by section heading in the phase file. Also re-read skills/memo/PHASE-MACHINE.md at each boundary (control-flow authority), same as the memo skill.
Parse argument
Read $ARGUMENTS. Parse it as:
- first whitespace-delimited token →
task_id(the slug of the working directory;task_idalways starts withmemo-); - remaining text, if any → explicit intake or plan-review response (
answer: <facts>,proceed,approve,cancel, oredit: <instructions>).
Task discovery (where to find the working directory)
The plugin used to stage tasks under ${CLAUDE_PLUGIN_DATA}/work/ then copy them to the user output folder at the end. As of v0.0.29 there is no staging — every task lives directly in the user's output folder from Phase 1 onwards.
Resolution order (first writable that contains a matching <task_id> directory wins):
$CLAUDE_PLUGIN_OPTION_OUTPUT_FOLDER/<task_id>/(plugin option set by the user).$MEMOFORGE_OUTPUT_FOLDER/<task_id>/(environment variable).$HOME/Documents/memoforge/<task_id>/(default for desktop installs).outputs/memoforge-work/<task_id>/(sandbox fallback, relative to CWD).<WORK_DIR>/(legacy fallback for tasks created before v0.0.29).
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 · 605 lines · 45 tokens per session scan A 6f4a9c282ca4
continue is a skill published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 13,372 once invoked, about $0.0002 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
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…