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 agentmods add skills/postindustria-tech/agentic-toolkit/neograph-dev-bug-fixnpx skills add postindustria-tech/agentic-toolkit --skill neograph-dev-bug-fixgit clone --depth 1 https://github.com/postindustria-tech/agentic-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/postindustria-tech/agentic-toolkit/neograph-dev-bug-fix)<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/neograph-dev-bug-fix"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/neograph-dev-bug-fix.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.01229 |
| Opus 5 | $0.00044 | $0.00615 |
| Sonnet 5 | $0.00017 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
neograph-dev-bug-fix 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 3d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neograph Bug Fix Workflow
Encodes the TDD bug fix process with neograph-specific gates. Every bug fix in this codebase follows the same sequence: reproduce with a failing test, trace the root cause, fix minimally, verify via mutation, run full suite.
The Invariant
Tests must fail BEFORE the fix, pass AFTER, and fail again when the fix is reverted. This is the mutation verification protocol. A test that never produced a FAILED output is not a regression test.
The Workflow
Step 1: Reproduce with a failing integration test
Write a test that demonstrates the bug through the full dispatch chain, not just the unit function. Neograph bugs almost always manifest at the boundary between layers (rendering + prompt compilation, lint + runtime keys, compile + checkpoint).
# WRONG: unit test that calls the function directly
result = _resolve_var("claim.text", {"claim": rendered_string})
assert result == "" # this passes but doesn't catch the real bug
# RIGHT: integration test through the full pipeline
graph = compile(construct)
result = run(graph, input={"node_id": "test"})
# Assert on what the LLM actually received, not intermediate values
Verify the test FAILS before proceeding. Print the failure output. Record it.
Step 2: Trace the root cause
Identify the exact line where behavior diverges from expectation. For neograph, the common divergence points are:
| Symptom | Likely location |
|---|---|
| Wrong data shape in prompt | _dispatch.py:_render_input or renderers.py:render_input |
| KeyError in template | _llm.py:_resolve_var or consumer's prompt_compiler |
| Missing field in state | state.py:compile_state_model or factory.py:_extract_input |
| Type mismatch at assembly | _construct_validation.py:_check_fan_in_inputs |
| DI param not found | decorators.py:_classify_di_params or runner.py:_inject_input_to_config |
Step 3: Fix minimally
Change only what is necessary. Do not refactor surrounding code. Do not add error handling for scenarios that are not part of the bug. Do not clean up nearby code.
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.
- 3d ago First seen · 144 lines · 87 tokens per session scan A ab95f0a97744
neograph-dev-bug-fix is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,229 once invoked, about $0.0004 per session on Opus 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
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
tdd
Test-driven development (TDD) process used when writing code. Use whenever you are adding any new code, unless the user explicitly asks to skip TDD or the code is exploratory/spike.
growing-outside-in-systems
Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent…
plan-create
Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…