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/quangphu1912/codebase-analyzer/analyze-agent-loopnpx skills add quangphu1912/codebase-analyzer --skill analyze-agent-loopgit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat 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 | $0.00034 | $0.01302 |
| Opus 5 | $0.00017 | $0.00651 |
| Sonnet 5 | $0.00007 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
analyze-agent-loop 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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to analyze the agent loop."
Overview
Map the runtime execution spine: how does a request enter, get processed, and produce output? Identify the turn loop, state machine, and tool continuation patterns.
Prerequisite: Reads docs/analysis/artifact-classification.md (need to know core vs support).
Process
- Identify the main entry point and request handler
- Trace the turn/request loop: input -> processing -> tool call -> response -> next turn
- Map state transitions: idle -> active -> waiting -> responding -> idle
- Find tool continuation patterns: when does the system call another tool after receiving output?
- Identify termination conditions: when does the loop stop?
- Find state persistence: what survives between turns?
- Produce execution spine diagram
State Machine Decomposition
Break the agent loop into discrete states and map every transition between them. The canonical state cycle is:
IDLE -> RECEIVING -> PROCESSING -> TOOL_CALL -> WAITING -> RESPONDING -> IDLE
For each state, identify:
- Entry condition -- what causes the system to enter this state?
- Actions -- what work happens while in this state?
- Exit transitions -- what are the possible next states, and what triggers each?
- Error paths -- what happens on failure within this state?
State Transitions:
IDLE --[new message]--> RECEIVING
RECEIVING --[parsed]--> PROCESSING
PROCESSING --[tool needed]--> TOOL_CALL
PROCESSING --[text reply]--> RESPONDING
PROCESSING --[error]--> ERROR
TOOL_CALL --[dispatched]--> WAITING
WAITING --[tool result]--> PROCESSING (continuation)
WAITING --[timeout]--> ERROR
RESPONDING --[sent]--> IDLE
ERROR --[retry]--> RECEIVING
ERROR --[fatal]--> IDLE (terminal)
Look for states that are implicit rather than explicit -- code that behaves like a state machine without naming states is harder to debug. Identify any states not covered by the canonical cycle (e.g., RATE_LIMITED, CANCELLED, STREAMING).
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.
- 2d ago First seen · 132 lines · 34 tokens per session scan A 3102bc750c8f
analyze-agent-loop is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,302 once invoked, about $0.0002 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…