trueline-workflow

trueline-workflow is a skill for Claude Code from rjkaes/trueline-mcp. It costs 95 tokens per session (1,430 once invoked), scanned A, original, Apache-2.0.

A workflow for using Trueline tools to read, search, edit, outline, verify, and inspect changes in files. Trueline checks references against file hashes so edits can be tied to the exact text that was read.

In plain words
What is it for?
Exploring files, making hash-verified edits, checking changes, and using the Trueline command-line tool in scripts, CI pipelines, or Git hooks.
Why use it?
It reduces mistakes from editing outdated or misremembered file content and explains the safe order for searching before editing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the trueline-mcp plugin — 1 skill, 4 hooks shipped together

Good fit Exploring files, making hash-verified edits, checking changes, and using the Trueline command-line tool in scripts, CI pipelines, or Git hooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rjkaes/trueline-mcp/trueline-workflow
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 rjkaes/trueline-mcp --skill trueline-workflow
Clone the repo
git clone --depth 1 https://github.com/rjkaes/trueline-mcp

Made for: Claude Code.

Or install trueline-mcp, the plugin that ships this one along with the rest of its 1 skill, 4 hooks.

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 trueline-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjkaes/trueline-mcp/trueline-workflow"><img src="https://agentmods.dev/badge/skills/rjkaes/trueline-mcp/trueline-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 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 $0.00095 $0.01430
Opus 5 $0.00048 $0.00715
Sonnet 5 $0.00019 $0.00286
Haiku 4.5 $0.00010 $0.00143

Measured 11d ago against content hash b9a1f772d199, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

trueline-workflow 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 11d 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.

skills/trueline-workflow/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trueline Workflow

Trueline MCP tools replace built-in Read/Edit/Grep with hash-verified, streaming, ref-based equivalents. Catches hallucinated edits, cuts tokens. Use in right order.

CLI vs MCP

The same six tools are also available as a standalone trueline shell binary (at bin/trueline in the repo), useful for shell scripts, CI pipelines, and git hooks where no MCP-aware agent is running. The same hash-verification guarantees apply.

trueline outline <paths...>
trueline read <paths...> [--ranges 10-20]
trueline search <pattern> <paths...> [-i] [-r] [--multiline] [-C N]
trueline edit <path> --edits @file|-|<flat flags>
trueline verify <path> --refs ...
trueline changes [paths...]   # alias: diff

Every subcommand accepts --help/-h. Pass --json on any subcommand for {ok, result} machine-readable output. Exit codes: 0 ok, 1 search no match, 2 tool error, 3 usage error.

Never pipe trueline read/trueline search through head, tail, sed, grep, or any filter that drops lines. The ref checksum (e.g. ref: ab10-cd11/efghij) is printed at the end of the output. Truncating it loses the ref, which makes trueline_edit unusable — there is nothing valid to pass as ref. Read the full output; scope it with --ranges (CLI) or path:start-end (MCP) instead of piping.

Use MCP tools (this skill) for in-agent file work. Use the CLI for anything outside an agent context.

Tool cheat sheet

Tool Use when Why
trueline_outline First look, any file ~10-20 lines vs hundreds
trueline_search Know target string/symbol Lines with hash prefixes + refs, one call
trueline_read Need exact edit context Per-line hashes + checksums; globs and path:range
trueline_edit All edits Hash-verified, atomic; built-in Edit blocked by hook
trueline_verify Refs held across turns Checks staleness without re-read
trueline_changes Review vs git Symbol-level semantic diff

Read the full file on GitHub · 122 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. 11d ago First seen · 122 lines · 95 tokens per session scan A b9a1f772d199

Subscribe to this mod's changes

trueline-workflow is a skill published in the GitHub repository rjkaes/trueline-mcp (34 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,430 once invoked, about $0.0005 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 2026-08-30.