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/raisedadead/claude-code-plugins/rollnpx skills add raisedadead/claude-code-plugins --skill rollgit clone --depth 1 https://github.com/raisedadead/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 | $0.00051 | $0.01583 |
| Opus 5 | $0.00026 | $0.00792 |
| Sonnet 5 | $0.00010 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
roll 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ds:roll — TaskList persistence across sessions
Three verbs, standalone: a live dossier is optional.
Storage: <cwd>/.scratchpad/.tasklist-roll/<YYYY-MM-DD_HHMMSS>.tlr
Format (compact pipe-table v1):
# tlr v1
sid: <session-id>
doss: <live-dossier-slug or —>
ts: <ISO-timestamp>
trig: explicit | precompact | sessionend
| i | st | subject | desc | actv | dep |
|---|----|---------|------|------|-----|
| 1 | x | Fix sort | INDEX regen sort flag wrong | Fixing sort | — |
| 2 | ~ | Soft-block Vm.X | warn+confirm on stale §X | Soft-blocking Vm.X | — |
| 3 | . | Wire integration | apply T10/T11 | — | 1,2 |
State legend (matches dossier §T): .=pending · ~=in_progress · x=completed. — = absent / default (restore: desc/actv default to subject). dep = comma-sep i values of blocking tasks; — = none.
Verbs
dump
Snapshot the current Claude Code TaskList to a new .tlr file.
- Read the live TaskList via the
TaskListtool. - Per task capture
id,subject,description,activeForm,status,blockedBy. v1 dropsmetadataandowner. - Read the current live dossier slug for the
doss:header (—when there is none). - Render the pipe-table per the format above.
- Write atomically to
<cwd>/.scratchpad/.tasklist-roll/<YYYY-MM-DD_HHMMSS>.tlr— tmp + rename. - Report:
rolled: <relpath> (<N> tasks, <P> pending).
Idempotent — the timestamp namespaces the filename, so a re-run adds a file.
restore [<file>]
Recreate the TaskList from a .tlr file.
<file>when given, else the newest<ts>.tlrin<cwd>/.scratchpad/.tasklist-roll/.- No
.tlrpresent → say so and suggestdumpfirst. - Identity check: read the
doss:header. A slug (rather than—) that differs from the current live dossier slug (INDEX firstliverow) getsroll is from <doss>, current live is <slug> — restore anyway? (y/N), defaulting to no. A cross-dossier restore is usually a mistake. - Parse the pipe-table: skip header lines starting with
#or without a leading|, skip|---|separator rows, ignore unknown trailing columns. - Pass 1 (dedup by subject):
TaskListfirst, collecting existing subjects. A row whosesubjectis new getsTaskCreatewithsubject,description,activeForm(desc/actvdefaulting tosubjecton—); a row whose subject exists reuses that id. Recordold_i → ideither way. - Pass 2: every row with
status != "."getsTaskUpdatewith the mapped id and status (~ → in_progress,x → completed). - Pass 3: every row with a non-
—depgetsTaskUpdatewithaddBlockedBy: [<mapped-ids>], translated through the pass-1 map. - Report:
restored: <N> tasks from <file> (<created> new, <skipped> already present).
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 · 102 lines · 51 tokens per session scan A eb6c0ccec9af
roll is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 51 tokens to every session and 1,583 once invoked, about $0.0003 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…