using-harness-anchor

using-harness-anchor is a skill for Claude Code from Redtropig/harness-anchor. It costs 32 tokens per session (1,374 once invoked), scanned A, original, MIT.

A project-work discipline that keeps track of the current state, scope, instructions, and verification evidence. It also provides platform-specific guidance for C and C++ work.

In plain words
What is it for?
Use it whenever working in a project to read its operating files first, preserve session state, respect scope boundaries, and apply the relevant verification and C/C++ guidance.
Why use it?
It reduces the chance of working in the wrong area, missing project rules, or claiming a change works without checking it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the harness-anchor plugin — 14 skills, 9 commands, 5 agents, 5 hooks shipped together

Good fit Use it whenever working in a project to read its operating files first, preserve session state, respect scope boundaries, and apply the relevant verification and C/C++ guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redtropig/harness-anchor/using-harness-anchor
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 Redtropig/harness-anchor --skill using-harness-anchor
Clone the repo
git clone --depth 1 https://github.com/Redtropig/harness-anchor

Made for: Claude Code.

Or install harness-anchor, the plugin that ships this one along with the rest of its 14 skills, 9 commands, 5 agents, 5 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 using-harness-anchor

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/redtropig/harness-anchor/using-harness-anchor"><img src="https://agentmods.dev/badge/skills/redtropig/harness-anchor/using-harness-anchor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,374 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 $0.00032 $0.01374
Opus 5 $0.00016 $0.00687
Sonnet 5 $0.00006 $0.00275
Haiku 4.5 $0.00003 $0.00137

Measured 11d ago against content hash 6a910d5e55c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

using-harness-anchor 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/using-harness-anchor/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using harness-anchor

You have the harness-anchor runtime layer, companion to superpowers (process methodology): it anchors state persistence, scope boundaries, verification gates, and C/C++ engineering.

Windows session (Git-Bash): plugin scripts already handle path and JSON-engine portability — do not hand-"fix" MSYS paths or shell out to PowerShell. C/C++ caveat: TSan/LSan are unavailable on this platform; read the cpp-sanitizers skill's Windows platform notes before trusting sanitizer coverage.

Priority Order

  1. User's explicit instructions (CLAUDE.md, direct requests) — highest
  2. superpowers skills (process)
  3. harness-anchor skills (state/scope/verification/cpp)
  4. Default system prompt — lowest

On apparent conflict, prefer superpowers' process and use harness-anchor to anchor state/evidence around it.

Project Navigation (read these BEFORE acting)

If they exist in the project root, read in this order:

  1. AGENTS.md or CLAUDE.md — operating manual
  2. feature_list.json — active feature + scope + done criteria
  3. PROJECT-TOC.md — file-level index, one line per file
  4. golden-rules.md — project taste / anti-pattern rules to honor
  5. session-handoff.md — what previous session left

If none exist, the project is un-anchored. Suggest the user run /anchor to scaffold.

Sibling Skills (load when triggered)

  • project-indexing — need to find files; PROJECT-TOC.md before Glob
  • feature-state-keeper — feature work starts/finishes; updates feature_list.json + progress.md
  • init-verification — at start of work; run init.sh health check
  • self-correction-loop — after edits that fail lint/build; iterate with evidence
  • anti-hallucination-gates — before claiming "done"; Default-FAIL evidence contract
  • test-coverage-design — what to test / is coverage real before "done"; dispatches coverage-analyst
  • capturing-golden-rules — a mistake recurs / a review comment is really a convention; encode it in golden-rules.md
  • context-budget-discipline — context fills up; SELECT/WRITE/COMPRESS/ISOLATE
  • docs-lookup — unfamiliar tools/APIs/errors; Context7 → WebSearch → calibrated-uncertainty chain
  • cpp-build-systems — CMake/Meson/Make/Bazel project
  • cpp-static-analysis — clang-tidy / cppcheck / IWYU
  • cpp-formatting — clang-format
  • cpp-sanitizers — ASan / UBSan / TSan / valgrind

Read the full file on GitHub · 86 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 · 86 lines · 32 tokens per session scan A 6a910d5e55c0

Subscribe to this mod's changes

using-harness-anchor is a skill published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,374 once invoked, about $0.0002 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.