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 waqas1412/claude-harness --skill refresh-seamsgit clone --depth 1 https://github.com/waqas1412/claude-harnessWrote 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/waqas1412/claude-harness/refresh-seams)<a href="https://agentmods.dev/skills/waqas1412/claude-harness/refresh-seams"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/refresh-seams/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/waqas1412/claude-harness/refresh-seams"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-harness/refresh-seams.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 | $0.00143 | $0.02691 |
| Opus 5 | $0.00072 | $0.01345 |
| Sonnet 5 | $0.00029 | $0.00538 |
| Haiku 4.5 | $0.00014 | $0.00269 |
Grade A, and why
refresh-seams 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refresh-seams: rebuild the workspace integration map
Discover, verify, and draw the cross-repo dependency graph. This skill never edits product code; it is grep-based evidence discovery plus mechanical verification plus map authoring. It is choreography: the main loop plans and delegates, hunter scan agents fan out concurrently, mechanical steps run as delegated helpers, and one strong agent redraws the map at the end. Do not build a coordinator or daemon. Invoking this skill by name is the explicit in-the-moment opt-in the global single-main-loop rule requires; it licenses the fan-out described below and nothing else.
Prerequisites and parameters
Read .claude/harness/seams/clusters.json (produced by workspace-init). It supplies: workspace root, the clusters map (name to repo-slug list), the vendored black-box set, excludes, the rulesFileConvention, and trackerPrefixes. Everything workspace-specific comes from this file; nothing about clusters, repo names, or hunter counts is hardcoded in this skill.
On first run, scaffold the pipeline assets from this skill's bundled assets/ into the workspace, but only if they are missing:
assets/discover.workflow.jsto.claude/harness/seams/discover.workflow.jsassets/build.pyto.claude/harness/seams/build.pyassets/cartographer-prompt.mdto.claude/harness/seams/cartographer-prompt.mdassets/verify-map.shto.claude/harness/seams/verify-map.shA workspace-local copy ALWAYS wins over the bundled one: if.claude/harness/seams/discover.workflow.jsalready exists, use it as-is. This lets a workspace tune hunters, kinds, or budgets without editing the shared plugin. (Directory-scoped skill precedence separately lets a workspace ship its ownrefresh-seamsskill that shadows this one; see MANIFEST.)
Scope argument
If given a scope (a cluster name, a subset of repo slugs, or a subset of hunter keys), pass it through as args.scope alongside args.config on the Workflow call in Phase 2 (Workflow(scriptPath, { args: { config, scope } })); discover.workflow.js reads both off the args global and filters both the hunter list and the flat cluster union down to the matching names before running discovery, then reconcile only those edges and merge into the existing seams.json rather than replacing untouched clusters. With no scope, pass only args: { config } and do a full rebuild (idempotent given the same code state).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +1 lines 5ed8abcb719e
- 10d ago First seen · 74 lines · 143 tokens per session scan A d2bbb9af7c61
refresh-seams is a skill published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 3d ago), licensed MIT. It adds 143 tokens to every session and 2,691 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-contract
Phase 4 — propose verifiable completion criteria and mandatory hard gates; reach AGREED (1-pass default, multi-round negotiation in --strict).