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 alexei-led/architect --skill tools-gitnexusgit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/tools-gitnexus)<a href="https://agentmods.dev/skills/alexei-led/architect/tools-gitnexus"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/tools-gitnexus/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/alexei-led/architect/tools-gitnexus"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/tools-gitnexus.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 | $0.00120 | $0.01050 |
| Opus 5.5 | $0.00048 | $0.00420 |
| Sonnet 5.5 | $0.00024 | $0.00210 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
tools-gitnexus 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitNexus
gitnexus turns git history into a queryable graph: co-change relationships,
per-file change frequency, and the historical blast radius of a path. It is the
evidence source for "do changes actually stay inside the intended boundary?" and
a corroborating signal for the volatility axis of Balanced Coupling — domain role
sets volatility; churn only supports it, it never sets it.
Evidence dimension: change.
When to use
Use to score change_locality (do edits respect module boundaries over history),
to ground volatility claims, and to find fragile seams where distant modules
co-change repeatedly. A module that churns and co-changes with a distant module
is a coupling risk only history can show. Build the index during the system-map
step.
Commands
Prefer exposed GitNexus runtime tools when available; use the CLI otherwise. Build or refresh indexes only in an approved writable cache/store.
gitnexus analyze # mine history → build the change graph
gitnexus status # index health + commit it covers
gitnexus list # entities/files known to the graph
gitnexus query "<expr>" # query co-change / frequency
gitnexus context <path> # what co-changes with <path>
gitnexus impact <path> # historical blast radius of a change
gitnexus detect-changes # files changed since the indexed commit
gitnexus cypher "<query>" # raw Cypher for custom graph questions
Flow: analyze, then status, then context / impact / cypher for
co-change evidence.
Stale-index handling
Run gitnexus status (and detect-changes) before trusting output. If the
index lags the working tree, co-change data is incomplete:
- Re-run
gitnexus analyzeto refresh, only if it can write to an approved cache/store. - If you cannot refresh, the change dimension is
tools_failed("stale index") — do not score change locality from it.
Evidence output
Record:
dimension: change.source: GitNexus status/freshness, query/context/impact command, and history window.facts: co-change pairs, churn hotspots, historical blast radius, or confirmed absence.limits: stale index, shallow clone, rename split, short history window, or failed analysis.
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.
- 1mo ago First seen · 105 lines · 120 tokens per session scan A a3b08271da3e
tools-gitnexus is a skill published in the GitHub repository alexei-led/architect (3 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 1,050 once invoked, about $0.0005 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 skills, from other repositories
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
sync-upstream
Reconcile this repo's forked skills with a new upstream release. Use when the user says an upstream (compound-engineering, mattpocock/skills) was updated, asks to merge/sync upstream changes into the forks, or wants the forks' divergence audited.