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 techygarg/lattice --skill bug-fixgit clone --depth 1 https://github.com/techygarg/latticeWrote 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/techygarg/lattice/bug-fix)<a href="https://agentmods.dev/skills/techygarg/lattice/bug-fix"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/bug-fix/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/techygarg/lattice/bug-fix"><img src="https://agentmods.dev/badge/skills/techygarg/lattice/bug-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.02618 |
| Opus 5.5 | $0.00031 | $0.01047 |
| Sonnet 5.5 | $0.00015 | $0.00524 |
| Haiku 4.5 | $0.00008 | $0.00262 |
Grade A, and why
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 15d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix
Required Skills
Load these skills based on bug scope:
framework:knowledge-priming-- Load project context so the diagnosis grounds in the real codebase. (always)framework:context-anchoring-- Find and load the feature's context doc; capture diagnosis and repair decisions in it. (always)framework:learning-harvest-- Load prior operational learnings at session start; harvest new ones at session end. (always)framework:collaborative-judgment-- Surface hypotheses and repair trade-offs as structured options instead of silently assuming. (always)framework:clean-code-- Keep the fix focused, readable, and free of drive-by changes. (always)framework:test-quality-- Regression tests, characterization baseline, assertion quality. (always)framework:architecture-- Layer placement and dependency direction. (conditional: layer placement is in question — Steps 2/4/5)framework:domain-driven-design-- Domain invariants and aggregate behavior. (conditional: domain invariants involved — Steps 2/5)framework:secure-coding-- Trust bounds and sensitive data handling. (conditional: trust boundary crossed — Steps 2/5)
Additional Instructions
STOP: Before Step 1, read additional_instructions.bug_fix (one line or a list) from .lattice/config.yaml. No file or no key → skip silently.
When lines are found:
- Show them verbatim under "Additional instructions (from config):".
- Highest priority — apply them for the whole session, including on resume. On any conflict with anything else in this skill — steps, gates, STOP rules — or with its Required Skills, standards documents, or operational learnings, the config line wins.
Workflow
Step 1: Establish Bug Context
Start from the failure, not from a proposed fix.
- Gather the observed behavior, the expected behavior, the reproduction path, and any evidence: failing test, error message, stack trace, log excerpt, request payload, recent change.
- Run
framework:learning-harvestLoad behavior. Focus hint: "bug investigation — focus: reliability, quality signals". - Run
framework:context-anchoringDocument Discovery to check for an existing context doc covering the affected feature/module:- Found → Load behavior. Honor every logged decision and constraint as an active commitment while diagnosing. An open investigation of this same bug is already logged in it → confirm with the user whether to resume that investigation or start fresh.
- Not found → Proceed from the bug report and the current code. Do not block diagnosis on a missing context doc.
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.
- 15d ago Changed · +9 lines af0741220ab7
- 1mo ago First seen · 188 lines · 77 tokens per session scan A f489e9320795
bug-fix is a skill published in the GitHub repository techygarg/lattice (209 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,618 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
session-profiler
Profile and debug Hermes sessions from their JSONL transcripts. Find a session and its subagents, build a queryable event table, summarize the work as a hierarchical table of contents, break down wall time, inference, tools, tokens, and estimated cost per agent, identify errors and improvement opportunities, and…
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Find the root cause of Elixir/Phoenix bugs — crashes, exceptions, stack traces, compile errors, LiveView that won't update, silent failures. Use when something is broken or misbehaves. --parallel for 4 tracks.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.