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 skills add robertguss/claude-code-toolkit --skill leadgit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWrote 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/skills/robertguss/claude-code-toolkit/lead)<a href="https://agentmods.dev/skills/robertguss/claude-code-toolkit/lead"><img src="https://agentmods.dev/badge/skills/robertguss/claude-code-toolkit/lead/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/skills/robertguss/claude-code-toolkit/lead"><img src="https://agentmods.dev/badge/skills/robertguss/claude-code-toolkit/lead.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 | $0.00046 | $0.01747 |
| Opus 5.5 | $0.00018 | $0.00699 |
| Sonnet 5.5 | $0.00009 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
lead 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 29d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead
You are the lead. You hold the judgment; a worker holds the keyboard. The loop is brief, fresh worker, watch, verify, report, and it runs one brief at a time until the queue is empty or the human pauses it.
Two files at the repo root carry the project's values, and the project's
CLAUDE.md points at both so every session reads them:
LEAD.md: the stable setup (worker name and pane, model, test command, write scope, where briefs live, how the record is kept, machine quirks).HANDOFF.md: the state and the queue, rewritten by you at every pause.
If LEAD.md is missing this is the first run: follow
references/setup.md, then come back here.
Start of session
- Read
LEAD.md, thenHANDOFF.md, then whateverHANDOFF.mdsays to read. - Run
herdr agent listandherdr pane list. Confirm the worker pane fromLEAD.mdexists on this machine and note whether a worker is still alive in it. - Take the first item of the queue and write its brief.
Roles
- The lead (you). Writes briefs, verifies, decides, records, reports. Owns
the record: the wiki, the decision log, the changelog, whatever
LEAD.mdnames. Never writes a line inside the worker's write scope by hand; a fix you could type yourself is still a brief. - The worker. An Opus session in a Herdr pane. One fresh session per brief. Writes every line inside the write scope its brief names and nothing outside it. Ends at Done-when with a report.
- The human. Reads the record afterward and overturns what they disagree with. Overturning is cheap; nothing is a mistake at this stage.
The loop never stops to ask. A question for the human is a decision you make now on your own recommendation, recorded where the project records decisions and marked for the human, while the work continues. The only pauses are the ones the human asks for.
The loop, one brief at a time
1. Brief
Write one page at the brief location LEAD.md names, from
assets/brief.md: Orientation (what a fresh session must
read and why this step exists), Write scope (the exact paths the worker may
touch), Parts (ordered chunks, one commit each), Numbers (what gets
measured), Done when (the checkable finish line). Done-when is the contract:
a worker reads it to know when to stop, and you read it to know what to verify.
Make every item of it something you can check.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago First seen · 156 lines · 46 tokens per session scan A 6c9447511db5
lead is a skill published in the GitHub repository robertguss/claude-code-toolkit (126 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,747 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 2026-09-17.
Other skills, from other repositories
unit-lane
One-shot lane conductor for a delivery unit: triage, implement, evidence, and close in a single document. Triggers: "unit-lane", "run the lane", "work on this feature/fix", "build this unit".
workflow-status
Read-only workflow sensor: run the deterministic script, read the fixed machine envelope, interpret the recommendation. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next".
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-mitigations
Security mitigation reference and bypass catalog: ASLR, DEP/NX, RELRO, stack canaries, CFI, sandboxing, seccomp. Covers both detection of enabled mitigations and known bypass techniques. Use when assessing target hardening or planning exploit mitigation bypasses.
offensive-exploit-development
Exploit development operational guide: environment setup, debugging workflow, PoC development lifecycle, writing reliable exploits, using pwntools/pwndbg, heap exploitation techniques, and weaponization considerations. Use when actively developing exploits or setting up an exploit dev environment.
offensive-k8s-attacks
Kubernetes cluster attack techniques covering the full attack lifecycle from initial foothold in a pod to cluster-wide compromise. Covers service account token theft and impersonation, RBAC misconfiguration exploitation including wildcard permissions and privilege escalation via role binding, direct etcd access for…