Publish Sign in

Impact Analysis with GitNexus

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code.

You say
Install this skill Read the source first Free Written by abhigyanpatwari · unverified publisher
Context cost
1.6k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 6.6 kBtext throughout, nothing executable
Licence
Source-availablefree to use
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Guardrail

Constrains what the agent is allowed to do.

securitytesting
Filed under

Security & Testing

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md6.5 kB · 159 lines
--- name: gitnexus-impact-analysis description: "Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"" ---
6# Impact Analysis with GitNexus
7
8## When to Use
9
10- "Is it safe to change this function?"
11- "What will break if I modify X?"
12- "Show me the blast radius"
13- "Who uses this code?"
14- Before making non-trivial code changes
15- Before committing — to understand what your changes affect
16
17## Bind the repository first
18
19Impact analysis is the gate that authorizes an edit, so it must answer for the
20repository you are about to edit.
21
22Call list_repos {} before the first tool call. With one indexed repository,
23use the examples below as written. With more than one, pass repo on every
24call: an omitted repo normally errors, but under an MCP policy with a
25configured default it resolves to that default silently. If you cannot tell
26which repository is meant, stop and ask — every result below an ambiguous
27identity inherits the ambiguity. list_repos is paginated, so page with
28offset: pagination.nextOffset until hasMore is false before concluding a
29repository is absent.
30
31detect_changes takes worktree when your changes are in a linked worktree
32the MCP server was not launched from. The server auto-detects a worktree only
33when it was launched from inside one; otherwise git diff runs in the wrong
34checkout and reports zero changed symbols — a false clean check that carries
35none of the degradation flags described below. In the CLI fallbacks, --repo .
36means the current checkout; pass the intended repository path instead when you
37are not standing in it.
38
39State the bound identity with your risk report:
40
41```
42Repository: <name> (<path>) Worktree: <path> Index: <commit>, <n> behind HEAD
43```
44
45## Workflow
46
47```
480. list_repos {} → Bind repo (and worktree)
491. impact({target: "X", direction: "upstream"}) or node .gitnexus/run.cjs impact "X" --direction upstream --repo .
502. READ gitnexus://repo/{name}/processes → Check affected execution flows
513. detect_changes({scope: "all"}) or node .gitnexus/run.cjs detect-changes --scope all --repo .
524. Assess risk and report to user, echoing repo/worktree/index identity
53```
54
55> If "Index is stale" → run node .gitnexus/run.cjs analyze in terminal.
56> If .gitnexus/run.cjs is missing, replace node .gitnexus/run.cjs with npx gitnexus in the fallback commands.
57
58## Checklist
59
60```
61- [ ] list_repos {} — bind repo; explicit repo when >1 indexed, ask if ambiguous
62- [ ] impact({target, direction: "upstream"}) or CLI fallback to find dependents
63- [ ] Review d=1 items first (these WILL BREAK)
64- [ ] Check high-confidence (>0.8) dependencies
65- [ ] READ processes to check affected execution flows
66- [ ] detect_changes({scope: "all"}) or CLI fallback for pre-commit check
67- [ ] Confirm the checkout you edited is the checkout that was diffed
68- [ ] Assess risk level and report, stating repo/worktree/index identity
69```
70
71## Understanding Output
72
73| Depth | Risk Level | Meaning |
74| ----- | ---------------- | ------------------------ |
75| d=1 | **WILL BREAK** | Direct callers/importers |
76| d=2 | LIKELY AFFECTED | Indirect dependencies |
77| d=3 | MAY NEED TESTING | Transitive effects |
78
79## Risk Assessment
80
81| Affected | Risk |
82| ------------------------------ | -------- |
83| <5 symbols, few processes | LOW |
84| 5-15 symbols, 2-5 processes | MEDIUM |
85| >15 symbols or many processes | HIGH |
86| Critical path (auth, payments) | CRITICAL |
87| **Zero callers found** | **UNKNOWN** |
88
89UNKNOWN is not a low rung on this scale — it means the walk could not answer.
90An empty caller set is equally consistent with "genuinely unused" and "the
91callers are not resolvable by the index" (plain-object property access, dynamic
92dispatch, cross-language calls), so few-callers ⇒ LOW does **not** apply. The
93result carries a riskNote saying so. Confirm with a text search before
94treating the symbol as safe to change or delete.
95
96## Tools
97
98**impact** — the primary tool for symbol blast radius. If MCP is unavailable, use node .gitnexus/run.cjs impact <symbol> --direction upstream --repo . instead:
99
100```
101impact({
102 target: "validateUser",
103 repo: "my-app", // required once >1 repository is indexed
104 direction: "upstream",
105 minConfidence: 0.8,
106 maxDepth: 3
107})
108
109→ d=1 (WILL BREAK):
110 - loginHandler (src/auth/login.ts:42) [CALLS, 100%]
111 - apiMiddleware (src/api/middleware.ts:15) [CALLS, 100%]
112
113→ d=2 (LIKELY AFFECTED):
114 - authRouter (src/routes/auth.ts:22) [CALLS, 95%]
115```
116
117**detect_changes** — git-diff based impact analysis. If MCP is unavailable, use node .gitnexus/run.cjs detect-changes --scope all --repo . instead:
118
119```
120detect_changes({scope: "all"})
121
122→ Changed: 5 symbols in 3 files
123→ Affected: LoginFlow, TokenRefresh, APIMiddlewarePipeline
124→ Risk: MEDIUM
125```
126
127Add repo once more than one repository is indexed, and `worktree: "<abs
128path>"` when your changes are in a linked worktree the server was not launched
129from.
130
131partial: true (a graph query failed) or truncated: true (the changed-symbol
132listing was capped) means the result is short of the truth, and reads like
133UNKNOWN above: a zero there means unseen, not unaffected. Re-run it rather
134than tick the pre-commit check.
135
136A wrong-worktree zero carries neither flag and is shape-identical to a genuine
137clean result, so confirm the checkout you edited is the one that was diffed
138before treating an empty change set as a passed check.
139
140## Example: "What breaks if I change validateUser?"
141
142```
1430. list_repos {}
144 → total: 2 (my-app, billing-api) — both define validateUser, so bind explicitly
145
1461. impact({target: "validateUser", repo: "my-app", direction: "upstream"}) or node .gitnexus/run.cjs impact "validateUser" --direction upstream --repo .
147 → d=1: loginHandler, apiMiddleware (WILL BREAK)
148 → d=2: authRouter, sessionManager (LIKELY AFFECTED)
149
1502. READ gitnexus://repo/my-app/processes
151 → LoginFlow and TokenRefresh touch validateUser
152
1533. Risk: 2 direct callers, 2 processes = MEDIUM
154 Repository: my-app (/abs/path/my-app) Worktree: same Index: current
155```
156
157With a single indexed repository, step 0 returns total: 1 and the repo
158argument drops out of every call above.
159
In the file
SKILL.md963 words
Files2
LicenceSource-available
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,580
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
0.83%
of a 200k window
Ten skills this size would take about 8% of the window before you open a file.
050k100k150k200k context window

1.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 6.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md6.5 kB
  • mcp.json0.1 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing. The Source-available licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Impact Analysis with GitNexus · 1.6k tokens when loaded npx mcprush@latest skill add abhigyanpatwari/impact-analysis-with-gitnexus

Writes to .claude/skills/impact-analysis-with-gitnexus/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceabhigyanpatwari/impact-analysis-with-gitnexus

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

AB
abhigyanpatwari

Publishes on mcprush.

0 servers listed5 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill