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 githits-com/githits-cli --skill githits-codegit clone --depth 1 https://github.com/githits-com/githits-cliWrote 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/githits-com/githits-cli/githits-code)<a href="https://agentmods.dev/skills/githits-com/githits-cli/githits-code"><img src="https://agentmods.dev/badge/skills/githits-com/githits-cli/githits-code/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/githits-com/githits-cli/githits-code"><img src="https://agentmods.dev/badge/skills/githits-com/githits-cli/githits-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00066 | $0.02322 |
| Opus 5.5 | $0.00026 | $0.00929 |
| Sonnet 5.5 | $0.00013 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
githits-code 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 7d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use GitHits for evidence from real open-source code instead of guessing from model memory.
CLI Invocation
- Run commands as
githits .... - If
githitsis not found, retry the same command asnpx -y githits@latest .... - Keep default text when the model reads results or chooses follow-ups. Use
--jsononly when code consumes the raw response or text omits a required field. - Do not expose credentials. If auth is required interactively, run
githits login; usegithits login --no-browseronly when the user can complete the printed URL flow. In noninteractive eval/CI, do not start OAuth; report thatGITHITS_API_TOKENor prior login is required. - If a command returns
TERMS_ACCEPTANCE_REQUIRED, rungithits settings terms acceptor use the returned authenticated acceptance URL, then retry once.
Decision Flow
- Need a canonical target for an OSS dependency name: use
githits resolve "<name>"; skip resolution for known canonical targets. Reuse only an unambiguous EXACT/HIGH best with CLEAR or NOT_APPLICABLE malicious-content status. Other or missing statuses are non-actionable; narrow or explicitly choose an actionable candidate for MEDIUM/LOW or ambiguity. Never auto-select, and do not treat CLEAR as vulnerability-free. A selectedsite:is docs-only. - Need a canonical cross-project example or pattern:
githits example "<focused question>"; include source repositories/citations from GitHits' generated references/provenance section. If GitHits cannot match--lang, retry with a suggested language from the error, or omit--lang. - Need package metadata, vulnerability/advisory status, dependency graphs, or release notes: stop and use the
githits-packageskill instead. - Exploring a topic in a known dependency or public repository: use
githits searchscoped by--in. - Searching an exact standalone documentation site: use
githits search "<topic>" --source docs --in site:<host[/path]>. If the result reports suggested site targets, retry one explicitly; suggestions are advisory targets, not aliases. - Need file/path enumeration: use
githits list <target> [paths...]; add--recursiveto traverse directories. Do not probe directories withgithits read. - Need exact source changes between versions or refs: use
githits code diff <unversioned-target> <from>..<to>. This is repository-wide even for package targets; use a repository-relative glob after--to narrow known paths. - Know the pattern:
githits grep <pattern> <targets...>uses RE2 regex, case-sensitive matching, and zero context. Use-Ffor literal text and-ito ignore case. Lookaround and backreferences are unsupported; multi-file regex needs a literal anchor. - Need documentation pages: use
githits search "<topic>" --source docs --in <target>for topic search, orgithits list site:<host[/path]>to browse a hosted site. Package/repositorylisttargets include their local documentation files. Read emitted targets and paths withgithits read;githits docs listremains a legacy package-page browser.
What ships with it
1 file 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.
- 7d ago Changed · +1 lines 3329ef226c31
- 10d ago Changed · +1 lines e5018c5502c0
- 11d ago Changed · +4 lines b8686e8dc974
- 15d ago Changed · -1 lines b5641f42d16c
- 17d ago Changed e8169a91a9be
- 18d ago Changed · +2 lines 57f6408629b4
- 21d ago Changed · +1 lines cea6934c4f55
- 23d ago Changed · +2 lines efb3dca7dd46
- 28d ago Changed 5990670d7037
- 29d ago First seen · 96 lines · 66 tokens per session scan A 2f0ef3d9db78
githits-code is a skill published in the GitHub repository githits-com/githits-cli (115 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 2,322 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.
nav-skill-creator
Analyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill for...", "automate this workflow", or "we keep doing X manually".
work
Execute an approved wish in dependency order with scoped workers, independent review, bounded repairs, and verified completion.
brainstorm
Explore an ambiguous idea with the user, settle scope and success criteria, and produce an independently reviewed design for wish.