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/dryvist/claude-code-plugins/replannpx skills add dryvist/claude-code-plugins --skill replangit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00100 | $0.01309 |
| Opus 5 | $0.00050 | $0.00655 |
| Sonnet 5 | $0.00020 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
replan 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 2d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replan
Rebuild a stale plan from reality. A plan file records what was true when written. Work moves on: items get done without the box being checked, a PR supersedes an approach, a claimed-live system turns out to have never shipped. Replanning re-derives ground truth, then rewrites the plan to match — it never edits the plan by trusting the plan.
Trigger: a plan drifted from reality — a step can outlive the decision that
banned it — or /resume surfaced contradictions between the plan and live state.
State warning: the plan is the least trustworthy source in the room. Derive from whichever ground-truth sources this environment actually has — then correct the plan.
Step 1: Re-derive ground truth (ignore the plan's claims)
Establish what is actually true right now, independent of what the plan says. Use every source available; skip the ones this environment does not have.
-
The artifact itself: read the file, run the test, hit the endpoint. This source always exists and outranks every claim about it.
-
Config vs running: a config default is not the running system. If the plan claims a capability is "live", check the thing itself (the mount, the secret, the endpoint), not the flag that would enable it. (This is the exact trap that makes plans go stale — a default read as a fact.)
-
Decisions: scan for anything that invalidates a plan step — a new rule, a closed ticket, a design the user changed mid-flight.
-
Version control (only when
git rev-parse --is-inside-work-treesucceeds): shipped work viagh pr list --state mergedplus the default-branch log; in-flight work via open PRs, their real mergeable/CI state, pushed branches, and worktrees. Run the resolution and its use as one block — they must share a shell (see ARCHITECTURE.md):default_branch=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null) default_branch=${default_branch#origin/} [ -n "$default_branch" ] || default_branch=$( gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name' 2>/dev/null) if [ -z "$default_branch" ]; then echo "default branch unknown — shipped work not derivable from git" elif ! git rev-parse --verify "origin/$default_branch" >/dev/null 2>&1; then echo "origin/$default_branch not fetched — run: git fetch origin $default_branch" else git log --oneline -30 "origin/$default_branch" fi
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.
- 2d ago First seen · 110 lines · 100 tokens per session scan A 01fd100c0bb0
replan is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,309 once invoked, about $0.0005 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
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…