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 marconae/speq-skill --skill speq-code-toolsgit clone --depth 1 https://github.com/marconae/speq-skillWrote 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/marconae/speq-skill/speq-code-tools)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-code-tools"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-code-tools/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/marconae/speq-skill/speq-code-tools"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-code-tools.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 | $0.00046 | $0.00487 |
| Opus 5.5 | $0.00018 | $0.00195 |
| Sonnet 5.5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
speq-code-tools 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 6d 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.
What it actually says
Code Tools
Semantic code navigation and editing via Serena MCP, if available. The user installs Serena globally, so the tool prefix varies (for example mcp__serena__find_symbol). This skill refers to the tools by short name below.
Before First Use Each Session
- These tools are deferred in this harness — a bare tool name has no loaded schema yet. Call
ToolSearchwith the queryserenato find them, then load the ones you need (select:<full tool name>, comma-separated for several) before calling them. - If
ToolSearchfinds no Serena tools, carry on with the generic tools (Read,Grep,Edit). Do not warn and do not stop.
Tool Preference
When Serena is available, use these instead of the generic alternative for anything this table covers. Symbol-level tools return exact definitions and references and edit whole symbols, where text search and line edits miss or break them.
| Task | Use |
|---|---|
| List directory | list_dir |
| Find files | find_file |
| File symbols | get_symbols_overview |
| Symbol definition | find_symbol |
| Symbol declaration | find_declaration |
| Symbol references | find_referencing_symbols |
| Interface/method implementations | find_implementations |
| LSP diagnostics for a file | get_diagnostics_for_file |
| Update function | replace_symbol_body |
| Insert after or before a symbol | insert_after_symbol, insert_before_symbol |
| Rename symbol | rename_symbol |
| Delete symbol | safe_delete_symbol |
| In-file text/regex replace | replace_content |
| Multi-file pattern replace | replace_in_files |
Memory tools (write_memory, read_memory, list_memories, delete_memory, edit_memory, rename_memory) exist and are available, but this project's specs (specs/, specs/_plans/.../notes/) are the source of truth — they are not part of this workflow.
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.
- 6d ago Changed · -1 lines · -5 tokens per session 8f6f818a389c
- 13d ago Changed · -11 lines d08d2cd94d1a
- 16d ago Changed · +1 lines · +3 tokens per session b50333595235
- 1mo ago Changed · +4 lines · -12 tokens per session d4d6c62125e9
- 1mo ago First seen · 44 lines · 60 tokens per session scan A 09a78ca9dba3
speq-code-tools is a skill published in the GitHub repository marconae/speq-skill (55 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 487 once invoked, about $0.0002 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
build-executor
Execute an active direct request or approved planned change. Native continuous implementation is the default; existing legacy changes retain their recorded contract obligations.
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
contract-builder
Maintain an execution contract only for an existing legacy change that requires one. New direct/planned changes do not invoke this skill when a contract is absent.
need-explorer
Clarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is comparing options, or the workflow needs a stable change definition before writing artifacts.
plan
Turns a reviewed spec or decided brief into ordered tasks for separate agent runs. Use for implementation tasks, tracker tickets, or useful milestones. Do not use for one coding task or its short execution outline.
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.