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 instructions/teaguesterling/fledgling/claude-mdgit clone --depth 1 https://github.com/teaguesterling/fledglingWhat 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 | $0.03604 | $0.03604 |
| Opus 5 | $0.01802 | $0.01802 |
| Sonnet 5 | $0.00721 | $0.00721 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade C, and why
fledgling CLAUDE.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- blq:agent-instructions --> How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fledgling: Project Conventions
Architecture
SQL macros first, MCP tools second. Every tool is backed by a reusable macro in sql/<tier>.sql. The tool publication in sql/tools/<tier>.sql is a thin wrapper using mcp_publish_tool(). Never put business logic in tool publications.
SQL Macro Files (sql/<tier>.sql)
File header
-- Fledgling: <Tier Name> Macros (<extension_name>)
--
-- Brief description of what this tier provides.
Per-macro comments
Every macro gets a block comment with: name, description, and examples.
-- macro_name: What it does in one line.
-- Additional context if needed.
--
-- Examples:
-- SELECT * FROM macro_name('arg1');
-- SELECT * FROM macro_name('arg1', 'arg2');
CREATE OR REPLACE MACRO macro_name(...) AS TABLE
...
Naming
- Macro names:
snake_case(SQL convention) - Column aliases:
snake_case - Use
AS TABLEfor all macros that return result sets - Use
:=for optional parameters with defaults - Avoid parameter names that shadow column names in the query body (use qualified
t.columnreferences or rename the parameter)
Tool Publication Files (sql/tools/<tier>.sql)
File header
-- Fledgling: <Tier Name> Tool Publications
--
-- MCP tool publications for <description>.
-- Wraps macros from sql/<tier>.sql.
mcp_publish_tool() call pattern
Always pass all 6 arguments:
SELECT mcp_publish_tool(
'ToolName', -- 1. PascalCase tool name
'Description for the agent.', -- 2. Tool description
'SELECT * FROM macro(...)', -- 3. SQL template
'{...}', -- 4. JSON Schema properties
'["required_param"]', -- 5. Required params list
'markdown' -- 6. Output format (always 'markdown')
);
Optional parameter handling (duckdb_mcp#19 workaround)
MCP tool params arrive as strings. Omitted params must be sent as the literal string 'null' by the test harness. Tool templates convert them back:
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 · 288 lines · 3,604 tokens per session scan C 564aee637f85
fledgling CLAUDE.md is an instructions file published in the GitHub repository teaguesterling/fledgling (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 3,604 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.