codestory-grounding

codestory-grounding is a skill for Claude Code, Codex from TheGreenCedar/CodeStory. It costs 52 tokens per session (2,277 once invoked), scanned A, original, Apache-2.0.

A skill that uses CodeStory to ground an AI agent in a local code repository before it makes claims, plans edits, selects tests, or reviews changes. CodeStory provides a repository map and broad code search.

In plain words
What is it for?
Use it when planning or reviewing repository changes, choosing tests, understanding architecture, or assessing the impact of an edit.
Why use it?
It helps the agent base its advice and changes on evidence from the actual repository instead of rediscovering or guessing about the codebase.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the codestory plugin — 1 skill shipped together

Good fit Use it when planning or reviewing repository changes, choosing tests, understanding architecture, or assessing the impact of an edit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thegreencedar/codestory/codestory-grounding
Install

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.

Any agent
npx skills add TheGreenCedar/CodeStory --skill codestory-grounding
Clone the repo
git clone --depth 1 https://github.com/TheGreenCedar/CodeStory

Made for: Claude Code, Codex.

Or install codestory, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for codestory-grounding

README.md
[![agentmods](https://agentmods.dev/badge/skills/thegreencedar/codestory/codestory-grounding/github.svg)](https://agentmods.dev/skills/thegreencedar/codestory/codestory-grounding)
Your own site
<a href="https://agentmods.dev/skills/thegreencedar/codestory/codestory-grounding"><img src="https://agentmods.dev/badge/skills/thegreencedar/codestory/codestory-grounding/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.

agentmods 80×15 button for codestory-grounding

Your own site · 80×15
<a href="https://agentmods.dev/skills/thegreencedar/codestory/codestory-grounding"><img src="https://agentmods.dev/badge/skills/thegreencedar/codestory/codestory-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02277
Opus 5.5 $0.00021 $0.00911
Sonnet 5.5 $0.00010 $0.00455
Haiku 4.5 $0.00005 $0.00228

Measured 24d ago against content hash f40ab6e90f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codestory-grounding 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 24d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/setup.ps1, scripts/setup.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/codestory/skills/codestory-grounding/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeStory Grounding

CodeStory helps an agent locate repository evidence, inspect source and follow relationships. The agent decides what to investigate and whether the evidence supports an answer. The skill does not expand the user's scope or authorize edits during a review.

Pass an absolute project root on every call. Keep project, source and publication identities attached when combining results across repositories.

Code-mode tools and results

Inspect selected tool declarations

When the needed operation is known, inspect its exact callable declaration. If you need an inventory first, print tool names, then inspect the declarations for the operations you choose. All operations remain available.

In hosts exposing ALL_TOOLS, a names-only inventory avoids printing every request and response schema:

text(ALL_TOOLS.filter(tool => /codestory/i.test(tool.name)).map(tool => tool.name));

After choosing an operation, match its actual exposed name exactly. This example selects search; choose any operation or set of operations the task needs:

const selectedNames = new Set(["mcp__codestory__search"]);
text(ALL_TOOLS.filter(tool => selectedNames.has(tool.name)));

Keep each selected declaration complete. Inspect further declarations when they become useful. A plugin-wide predicate over names and descriptions can print many unused declarations; discovery does not require displaying all of them. When a linked document path is already known, bound search to that file. Do not run a broad package or repository search merely to rediscover it.

Display each result payload once

Some hosts expose both content and structuredContent (or structured_content) to JavaScript. Printing the whole wrapper can put the same JSON payload into the model context twice.

Use one complete representation while retaining every other returned field. This example removes only plain text blocks that exactly match the serialized structured payload. Different spacing, key ordering or numeric spelling leaves the text in place; parsing it first could discard precision that only the text retains. Distinct text, annotations, images, resources, error flags and metadata stay intact. Keep the original result for programmatic use.

Read the full file on GitHub · 201 lines

Changes

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.

  1. 24d ago Changed · +8 lines f40ab6e90f33
  2. 27d ago Changed · +72 lines · +8 tokens per session 88db475d854f
  3. 1mo ago First seen · 121 lines · 44 tokens per session scan A 3f2cf1908125

Subscribe to this mod's changes

codestory-grounding is a skill published in the GitHub repository TheGreenCedar/CodeStory (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,277 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.

Related

Other skills, from other repositories

kivgraph

Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.

Luqueee/kivgraph · 39 tokens

memtrace-first

Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded…

syncable-dev/memtrace-public · 115 tokens

memtrace-style-fingerprint

Pull the codebase's empirical style norm from Memtrace and match it when writing or editing source code in an indexed repo. Use when choosing between competing idioms (ternary vs if-else, arrow vs function declaration, const vs let, await vs .then, early-return vs nested-return), matching naming case, or when the user…

syncable-dev/memtrace-public · 111 tokens

memtrace-decision-memory

Use Cortex decision memory through the normal Memtrace MCP tools. Trigger for free-text questions about what was decided, chosen, rejected, banned, or established as a convention; for why a symbol exists or which contracts constrain it; for whether a known decision held, drifted, or was violated; and for the…

syncable-dev/memtrace-public · 137 tokens

memtrace-evolution

Trace source-code change history from Memtrace's symbol-level temporal memory. Use when the user asks about change history, recent modifications, what changed since a date, symbol timeline, evolution, unexpected changes, or incident timelines. Do not use git log, git diff, Grep, or manual file search to reconstruct…

syncable-dev/memtrace-public · 107 tokens

memtrace-fleet-first

Coordinate fleets of coding agents sharing one repo+branch: publish typed intents, classify edit episodes, and resolve conflicts before they collide. Use FIRST when multiple agents work the same repo+branch, before reading/planning/editing, when joining a fleet or handing work off, and when the user says two agents…

syncable-dev/memtrace-public · 144 tokens