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 LiuYihey/Agent-Engineering --skill tool-call-fixgit clone --depth 1 https://github.com/LiuYihey/Agent-EngineeringWrote 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/liuyihey/agent-engineering/tool-call-fix)<a href="https://agentmods.dev/skills/liuyihey/agent-engineering/tool-call-fix"><img src="https://agentmods.dev/badge/skills/liuyihey/agent-engineering/tool-call-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/liuyihey/agent-engineering/tool-call-fix"><img src="https://agentmods.dev/badge/skills/liuyihey/agent-engineering/tool-call-fix.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 | $0.00081 | $0.01979 |
| Opus 5.5 | $0.00032 | $0.00792 |
| Sonnet 5.5 | $0.00016 | $0.00396 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
tool-call-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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Call Fix
Systematic playbook for "the agent said it would call a tool, but nothing happened" and related failures.
Works on any stack (raw SDK, LangChain, LangGraph, Vercel AI SDK, custom agent loops). Project-specific notes live in examples/ — add your own file there when adapting.
Core mental model
Prose and tool execution are two weakly coupled channels:
LLM stream
├─ text_delta → UI text (usually immediate)
├─ thinking_delta → "Thought for Ns" / hidden reasoning (immediate)
└─ tool_use block → parser → executor → tool card (often delayed)
Never infer tool execution from assistant prose. Only structured tool_use / function_call blocks count.
UI transcript ≠ LLM transcript. Chat history shown to users is often flattened text. The API needs structured blocks (thinking, tool_use, tool_result). Rebuilding API input from UI text alone causes Mode H — tools look "broken" on turn 2+ even when turn 1 worked.
Before you patch: classify the layer
Same user symptom can break at eight layers (A–H). Classify with logs before adding nudges, tool_choice: required, or prompt changes.
| Log / signal | Mode | Fix layer |
|---|---|---|
Raw stream has no tool block; stop_reason=end_turn |
A Wire prose-only | Model/guard; not parser |
| Turn 1 OK, turn 2+ degrades; flat API history | H Transcript loss | Persist native message chain |
tool_calls=1 but wrong name vs intent |
B Wrong tool | Routing/prompt; recovery won't fire |
| Right tool, executor rejects input | C Bad payload | Schema validation / coercion |
| Parser has tool block; UI late or silent mid-stream | D Stream bridge | Forward early tool events to UI |
| Second round in same turn breaks | E In-turn thinking loss | Preserve thinking + signature in working messages |
| Server logs exec; UI/DB silent | F Visibility filter | Align skip/hide lists across layers |
| Guard should fire; didn't | G Dead guard branch | Fix intent detection patterns |
What ships with it
3 files 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.
- 1mo ago First seen · 162 lines · 81 tokens per session scan A 4d7a2869622e
tool-call-fix is a skill published in the GitHub repository LiuYihey/Agent-Engineering (5 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,979 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.