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.
git clone --depth 1 https://github.com/FlorinI/Florians-Claude-Code-KitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/florini/florians-claude-code-kit/identity)<a href="https://agentmods.dev/commands/florini/florians-claude-code-kit/identity"><img src="https://agentmods.dev/badge/commands/florini/florians-claude-code-kit/identity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/florini/florians-claude-code-kit/identity"><img src="https://agentmods.dev/badge/commands/florini/florians-claude-code-kit/identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00060 | $0.02821 |
| Opus 5.5 | $0.00024 | $0.01128 |
| Sonnet 5.5 | $0.00012 | $0.00564 |
| Haiku 4.5 | $0.00006 | $0.00282 |
Grade A, and why
identity 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 28d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/identity
Manage the remembered session identity for this project — the name / color / model /
effort stored in <project>/.desk/session-identity.json. The cc launcher
(~/.claude/claude-launch.mjs) reads this file at launch to title and color the terminal tab and to
apply per-project --model / --effort.
Four fields, three surfaces:
- Remembered = the JSON file. Persists across sessions. Only a file edit changes it — that's what
/identitywrites. - Live (paste) =
name,color,model,effort— each has a built-in slash command that applies to the running session immediately:/rename,/color,/model <id>,/effort <level>. These have no programmatic API (anthropics/claude-code#58588) and the model cannot invoke them — so/identityfinishes by handing you the exact lines to paste.model/effortare also read by thecclauncher, which adds--model <id>/--effort <level>toclaudeat launch — so persisting them makes futurecclaunches start with that model/effort, while the paste-line changes this session now.
Arguments
$ARGUMENTS is free-form — parse it leniently:
show→ read-only: report all four fields and the paste-lines. Change nothing.- empty (no args) → report what's set, then run Interactive setup (below) for each unset
field. If all four are set, this collapses to
show. name ...→ set/replacename(everything up to a/,;, or acolor/model/effortkeyword; names may contain spaces).color ...→ set/replacecolor(one token).model ...→ set/replacemodel(one token — a Claude model id or alias passed verbatim toclaude --model, e.g.opus,sonnet,claude-opus-4-8). Accept any non-empty token.effort ...→ set/replaceeffort. Validate againstlow | medium | high | xhigh | max; if it isn't one of those, don't persist it — list the levels and ask.colors(orcolorwith no value) → render the swatch row from "Color" under Interactive setup, print the/color <name>line under it, and stop. Nothing is read or written. It is how the palette gets shown oncecoloris already set, since setup only runs for unset fields.- to clear a field:
<field> none(orunset) → remove that key. - any combination, in any order, separated by
/,;,,, or whitespace.
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.
- 28d ago Changed f1e89b836de2
- 29d ago Changed · +6 lines 54f54e649f8b
- 1mo ago Changed · +8 lines · -1 tokens per session 2f5a7dc937ec
- 1mo ago First seen · 161 lines · 61 tokens per session scan A 32bc41d27c90
identity is a command published in the GitHub repository FlorinI/Florians-Claude-Code-Kit (5 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 2,821 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
safe-build
Build the application for development or production.
create-task-list.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.