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 skills add Redtropig/harness-anchor --skill using-harness-anchorgit clone --depth 1 https://github.com/Redtropig/harness-anchorWrote 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.
[](https://agentmods.dev/skills/redtropig/harness-anchor/using-harness-anchor)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- User's explicit instructions (CLAUDE.md, direct requests) — highest
- superpowers skills (process)
- harness-anchor skills (state/scope/verification/cpp)
- 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:
AGENTS.mdorCLAUDE.md— operating manualfeature_list.json— active feature + scope + done criteriaPROJECT-TOC.md— file-level index, one line per filegolden-rules.md— project taste / anti-pattern rules to honorsession-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 Globfeature-state-keeper— feature work starts/finishes; updates feature_list.json + progress.mdinit-verification— at start of work; runinit.shhealth checkself-correction-loop— after edits that fail lint/build; iterate with evidenceanti-hallucination-gates— before claiming "done"; Default-FAIL evidence contracttest-coverage-design— what to test / is coverage real before "done"; dispatchescoverage-analystcapturing-golden-rules— a mistake recurs / a review comment is really a convention; encode it in golden-rules.mdcontext-budget-discipline— context fills up; SELECT/WRITE/COMPRESS/ISOLATEdocs-lookup— unfamiliar tools/APIs/errors; Context7 → WebSearch → calibrated-uncertainty chain
cpp-build-systems— CMake/Meson/Make/Bazel projectcpp-static-analysis— clang-tidy / cppcheck / IWYUcpp-formatting— clang-formatcpp-sanitizers— ASan / UBSan / TSan / valgrind
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.
- 11d ago First seen · 86 lines · 32 tokens per session scan A 6a910d5e55c0
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.
Other skills, from other repositories
remotion-upgrade
Upgrade Remotion, and related packages.
browser-tools
Security wrapper over the upstream agent-browser skill, adding URL blocklisting, rate limiting, robots.txt enforcement, and scraping guardrails. Use when automating browser workflows that need safety limits.
remotion-create
Creating a new Remotion video.
async-jobs
Async job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…