Claude Code Mods: What Blast Radius, Token Ledger and Context View Do
By Matt Cullerton, founder of Mavric and Apso
Claude Code mods are plugins that change how Claude Code looks and behaves, and Anthropic shipped them around October 1, 2026. A TikTok from @gbtalkstech presents three mods, token ledger, context view and blast radius, as if they all came with that launch. Only blast radius is Anthropic's, the video describes it wrongly, and it skips the security warning Anthropic puts first.
What are Claude Code mods?
"Mod" is Anthropic's own term. Its mods overview says: "A mod is a plugin that changes how Claude Code looks and behaves. It's made of JavaScript or TypeScript event handlers." It also says "Mods are on by default. In the terminal, use Claude Code v2.1.287 or later. The Desktop app includes its own copy of Claude Code, and mods work there from v2.1.286."
Mods sit alongside older extension points such as settings hooks, Agent Skills, subagents, slash commands, status lines and MCP servers. Those all run outside the Claude Code process. A mod runs inside it, which is why only a mod can draw a pane or restyle the spinner. The docs flag a naming overlap: "Claude Code calls both kinds hooks: on these pages, 'hook' means a mod's handler, and the settings-file kind is a 'settings hook'."
Which Claude Code mods are made by Anthropic?
Anthropic publishes three sample mods in the claude-code-playground repository: token-weather, blast-radius and replay-theater. It says the repository "shares them as they are, without support."
A separate set of built-in mods ships inside Claude Code and appears in /plugin under Built-in: cc-plugin-agents-md, cc-plugin-diff, cc-plugin-plugin-authoring, cc-plugin-sec-default, cc-plugin-telemetry and cc-plugin-you-should-know.
Neither list includes token ledger or context view. Both are community mods:
- token-ledger is published by GitHub user Arunjay4213 in the claude-mods repository.
- context-view is published by GitHub user kongyo2 and described as "The context window as one row above the prompt, drawn the way Claude Code draws its own meters."
Anthropic's own context-window mod is token-weather, which draws "a forecast of your context window above the prompt." The video moves its links to a comment, which I did not read, so these are the closest public matches by name.
What does the blast radius mod do?
The video says blast radius "tells you which files are being changed by a current code change." That is wrong. Anthropic describes it as a mod that "holds a risky shell command, such as rm -rf or a force push, and shows what it would change, with buttons to proceed or cancel."
The blast-radius README lists the commands it intercepts:
rm -r,rm -fandrm -rfgit reset --hard,git restore .,git cleanand agit checkoutthat discards the whole working tree- force pushes, including
-f,--force-with-leaseand+refsyntax - database migrations through
manage.py migrate,db:migrate,alembic upgradeandprisma migrate
For each, the pane shows what the command would destroy, such as the files a delete would remove with their count and total size, or the remote commits a force push would drop. The mod holds the tool.call event until you press Proceed or Cancel, and on cancel returns a denial with a reason Claude can act on.
To review which files an edit touched, Anthropic offers the replay-theater sample or the built-in /diff pane.
Does token ledger show your Claude Code usage limit?
No. The video says token ledger shows "how many tokens you're using and if you're approaching your session limit." The first half is right.
Its README shows a status line like $0.4799 session · last turn $0.2394 · 46k in / 5 out · cache 75%, plus a /ledger command that lists per-turn model, tokens, cache statistics, duration and cost. Those are spend figures for the session.
Plan limits are reported by a different mod in the same repository, quota-meter. It shows the 5-hour and 7-day rolling windows with percent used, reset times and burn-rate projections. The mods reference documents $.session.usage() as returning { startedAt, context, rateLimits, cost }, and a session.measure event that fires "After each turn, and when a plan limit's percent used changes."
Are Claude Code mods safe to install?
Anthropic's docs put the warning up front. A mod can "read and write files anywhere your user account can, start programs, and make network requests." It can read "environment variables and settings files, including an API key you keep in either," see "every prompt you send and every tool call Claude makes," and "approve a tool call before you're asked."
Mods also run outside any sandbox: "Mods aren't sandboxed. If you turn on sandboxing, the sandbox isolates the Bash commands Claude runs, and a process that a mod starts runs outside it."
To check a mod before loading it, clone its repository and run claude plugin validate ./some-mod. The hooks: and calls: lines list every event it handles and every mods API call it makes, without running the mod.
Bottom line
Mods are a real Anthropic feature, and blast radius is one of its three official samples. Blast radius stops destructive shell commands and shows what they would delete, while token ledger and context view are third-party mods with no support path. Run claude plugin validate on any mod before installing it.
Sources
- Mods overview - definition, versions, sample and built-in mods, and security warnings.
- Mods reference - events and the
$.session.usage()shape. - Anthropic sample mods - token-weather, blast-radius and replay-theater.
- blast-radius README - the commands it intercepts.
- token-ledger - community cost and token mod.
- quota-meter - community plan-limit mod.
- context-view - community context-window mod.
- Built-in mod source - Anthropic's built-in mods.
- The New Stack on Claude Code mods - launch coverage.
Published October 5, 2026. Based on a TikTok by @gbtalkstech. Full video notes (markdown)