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/nickmisasi/planner/continuenpx skills add nickmisasi/planner --skill continuegit clone --depth 1 https://github.com/nickmisasi/plannerWhat 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 | $0.00034 | $0.00774 |
| Opus 5 | $0.00017 | $0.00387 |
| Sonnet 5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continue work on an existing project or idea. This skill provides a selection interface so the user can choose exactly what to pick up.
Instructions
When the user invokes /continue, follow these steps:
1. Load the Registry
Read registry.yaml to get all projects and their ideas.
2. Present Project Selection
Use AskUserQuestion to let the user pick a project. Display options with project name and status. Include the number of active ideas for context in each option's description.
If the user provides an argument (e.g., /continue mattermost-plugin-agents), try to match it to a project slug or name and skip this step.
3. Present Idea Selection
Once a project is selected, use AskUserQuestion to let the user pick which idea to resume. Display options with:
- Idea name
- Current status/phase
- Last session date
Sort by last_session date (most recent first). Include an option for "Work on project-level context (no specific idea)" for cases where the user wants to update context.md or do general project planning.
4. Load Full Context
Once the idea is selected, read ALL of these files and internalize them:
projects/<project-slug>/project.yaml— Project metadataprojects/<project-slug>/context.md— Project-level contextprojects/<project-slug>/ideas/<idea-dir>/session.md— CRITICAL: This has the full conversation stateprojects/<project-slug>/ideas/<idea-dir>/MILESTONES.md— If this file exists, read it to understand prior milestone context. This tells you what work has already been completed and what carried forward.projects/<project-slug>/ideas/<idea-dir>/spec.md— Current specprojects/<project-slug>/ideas/<idea-dir>/assumptions.md— Current assumptions and confidenceprojects/<project-slug>/ideas/<idea-dir>/research.md— Research findings
5. Present Session Summary
After loading context, present to the user:
- Milestone Context: if MILESTONES.md exists, show which milestone we're on and a one-line summary of each prior milestone
- Current Phase: from session.md
- Summary of Progress: from session.md
- Open Questions: from session.md
- Next Steps: from session.md
- Assumption Confidence: overall score from assumptions.md (if iteration has started)
- Worktrees: if session.md has a
## Worktreessection, show the branch name and paths. Prompt the user to/add-dirthem if they haven't already.
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 · 67 lines · 34 tokens per session scan A bb1e442ceb93
continue is a skill published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 774 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 2026-08-31.
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…