agentmods.dev

stacklit

stacklit is a skill for Claude Code, Codex from glincker/stacklit. It costs 27 tokens per session (189 once invoked), scanned A, original, MIT.

A coding-agent skill that reads Stacklit's generated codebase map to locate relevant modules and inspect dependencies before searching or editing. Stacklit is a tool that records files, symbols, and dependency relationships in structured files.

In plain words
What is it for?
Use it to find modules by purpose, inspect dependencies and dependants, read repository hints, identify files not to change, and detect when the index is stale.
Why use it?
It helps avoid broad searches and shows which code may be affected by a change, including files that depend on the code being edited.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 131repo +17 5d ago A scan 27 tokens original MIT

Good fit Use it to find modules by purpose, inspect dependencies and dependants, read repository hints, identify files not to change, and detect when the index is stale.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glincker/stacklit/skill
View source ↗ glincker/stacklit stacklit.glinr.com
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 glincker/stacklit --skill skill
Clone the repo
git clone --depth 1 https://github.com/glincker/stacklit

Made for: Claude Code, Codex.

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 stacklit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/glincker/stacklit/skill"><img src="https://agentmods.dev/badge/skills/glincker/stacklit/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 189 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.
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 $0.00027 $0.00189
Opus 5.5 $0.00011 $0.00076
Sonnet 5.5 $0.00005 $0.00038
Haiku 4.5 $0.00003 $0.00019

Measured 4d ago against content hash d54b74e4af44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stacklit 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 4d 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.

internal/setup/skill/SKILL.md · 18 lines

What it actually says

Read stacklit.json before broad searches.

  1. Missing or stale: stacklit generate.
  2. Find the module by purpose, then read only its file_list.
  3. Before editing, check depended_by and dependencies.most_depended.
  4. New code goes where hints.add_feature says; verify with hints.test_command.
  5. Respect hints.do_not_touch.

MCP tools, if connected: get_overview, find_module, get_module, get_dependencies, list_modules, get_hot_files, get_hints.

Docs, APIs, schemas, owners: stacklit ingest, then read stacklit.context.json. Index drift: stacklit diff.

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. 4d ago First seen · 18 lines · 27 tokens per session scan A d54b74e4af44

Subscribe to this mod's changes

stacklit is a skill published in the GitHub repository glincker/stacklit (131 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 189 once invoked, about $0.0001 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 2026-11-09.

Memory and contextai-agentsclicode-intelligencecodebase-indexcursordependency-graph
Related

stacklit compared with skills from other repositories

stacklit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
stacklitglincker/stacklitSkill1315d agoMITA27Claude Code, Codex
shared-agents-knowledgenetgrade-digital/shared-agentsSkill513d agoMITA54Claude Code
scip-planPlunderStruck/scip-querySkill727d agoApache-2.0A36Codex
scip-integrity-auditPlunderStruck/scip-querySkill727d agoApache-2.0A44Codex
scip-queryPlunderStruck/scip-querySkill727d agoApache-2.0A27Codex
scip-architecture-reviewPlunderStruck/scip-querySkill727d agoApache-2.0A39Codex
scip-explorePlunderStruck/scip-querySkill727d agoApache-2.0A24Codex