Publish Sign in

Debugging with GitNexus

Use when the user is debugging a bug, tracing an error, or asking why something fails.

You say
Install this skill Read the source first Free Written by abhigyanpatwari · unverified publisher
Context cost
1.3k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 5.2 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 is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"

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.

Workflow

Runs a procedure end to end.

developer toolsdebugging
Filed under

Developer Tools & Repos

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.md5.2 kB · 132 lines
--- name: gitnexus-debugging description: "Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"" ---
6# Debugging with GitNexus
7
8## When to Use
9
10- "Why is this function failing?"
11- "Trace where this error comes from"
12- "Who calls this method?"
13- "This endpoint returns 500"
14- Investigating bugs, errors, or unexpected behavior
15
16## Bind the repository first
17
18A root cause traced in the wrong repository is a wrong root cause.
19
20Call list_repos {} before the first tool call. With one indexed repository,
21use the examples below as written. With more than one, pass repo on every
22call: an omitted repo normally errors, but under an MCP policy with a
23configured default it resolves to that default silently. If you cannot tell
24which repository is meant, stop and ask. This matters most for cypher, whose
25statement carries no in-band hint of which database it ran against.
26
27list_repos is paginated, so page with offset: pagination.nextOffset until
28hasMore is false before concluding a repository is absent.
29
30A stale index describes the code from before your bug, so refresh before
31trusting a trace, and state the repository and index freshness with the
32diagnosis.
33
34## Workflow
35
36```
370. list_repos {} → Bind repo
381. query({search_query: "<error or symptom>"}) → Find related execution flows
392. context({name: "<suspect>"}) → See callers/callees/processes
403. READ gitnexus://repo/{name}/process/{name} → Trace execution flow
414. cypher({statement: "MATCH path..."}) → Custom traces if needed
42```
43
44> If "Index is stale" → run node .gitnexus/run.cjs analyze in terminal.
45
46## Checklist
47
48```
49- [ ] list_repos {} — bind repo; explicit repo when >1 indexed, ask if ambiguous
50- [ ] Understand the symptom (error message, unexpected behavior)
51- [ ] query for error text or related code
52- [ ] Identify the suspect function from returned processes
53- [ ] context to see callers and callees
54- [ ] Trace execution flow via process resource if applicable
55- [ ] cypher for custom call chain traces if needed
56- [ ] Read source files to confirm root cause
57- [ ] State the repository and index freshness with the diagnosis
58```
59
60## Debugging Patterns
61
62| Symptom | GitNexus Approach |
63| -------------------- | ---------------------------------------------------------- |
64| Error message | query for error text → context on throw sites |
65| Wrong return value | context on the function → trace callees for data flow |
66| Intermittent failure | context → look for external calls, async deps |
67| Performance issue | context → find symbols with many callers (hot paths) |
68| Recent regression | detect_changes to see what your changes affect — pass worktree for a linked worktree |
69| "How does A reach B?" | trace between the two symbols — shortest call chain in one call |
70
71## Tools
72
73**query** — find code related to error:
74
75```
76query({search_query: "payment validation error", repo: "my-app"})
77→ Processes: CheckoutFlow, ErrorHandling
78→ Symbols: validatePayment, handlePaymentError, PaymentException
79```
80
81**context** — full context for a suspect:
82
83```
84context({name: "validatePayment", repo: "my-app"})
85→ Incoming calls: processCheckout, webhookHandler
86→ Outgoing calls: verifyCard, fetchRates (external API!)
87→ Processes: CheckoutFlow (step 3/7)
88```
89
90**cypher** — custom call chain traces. Pass repo alongside the statement; the
91Cypher text itself names no repository, so the result is unattributable without
92it:
93
94```cypher
95MATCH path = (a)-[:CodeRelation {type: 'CALLS'}*1..2]->(b:Function {name: "validatePayment"})
96RETURN [n IN nodes(path) | n.name] AS chain
97```
98
99**trace** — shortest call chain between two symbols ("how does A reach B?"), one call instead of chaining context hops:
100
101```
102trace({ from: "processCheckout", to: "fetchRates", repo: "my-app" })
103→ status: ok, hopCount: 3
104→ hops: processCheckout → validatePayment → verifyCard → fetchRates
105→ edges: CALLS (1.0), CALLS (0.95), CALLS (1.0)
106```
107
108When no path exists, trace reports the furthest reachable node — exactly where the chain breaks (dynamic dispatch, reflection, or an external boundary).
109
110## Example: "Payment endpoint returns 500 intermittently"
111
112```
1130. list_repos {}
114 → total: 2 (my-app, billing-api) — bind my-app explicitly on every call
115
1161. query({search_query: "payment error handling", repo: "my-app"})
117 → Processes: CheckoutFlow, ErrorHandling
118 → Symbols: validatePayment, handlePaymentError
119
1202. context({name: "validatePayment", repo: "my-app"})
121 → Outgoing calls: verifyCard, fetchRates (external API!)
122
1233. READ gitnexus://repo/my-app/process/CheckoutFlow
124 → Step 3: validatePayment → calls fetchRates (external)
125
1264. Root cause: fetchRates calls external API without proper timeout
127 Repository: my-app Index: current
128```
129
130With a single indexed repository, step 0 returns total: 1 and the repo
131argument drops out of every call above.
132
In the file
SKILL.md747 words
Files1
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.

≈60
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,240
on trigger
The instruction body, read only when the skill fires.
0.65%
of a 200k window
Ten skills this size would take about 7% of the window before you open a file.
050k100k150k200k context window

1.3k 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

1 file, 5.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md5.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file 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.

# Debugging with GitNexus · 1.3k tokens when loaded npx mcprush@latest skill add abhigyanpatwari/debugging-with-gitnexus

Writes to .claude/skills/debugging-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/debugging-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