Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chan4lk/specclaw/plugin install specclawWrote 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/chan4lk/specclaw/verify)<a href="https://agentmods.dev/skills/chan4lk/specclaw/verify"><img src="https://agentmods.dev/badge/skills/chan4lk/specclaw/verify.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.02243 |
| Opus 5 | $0.00027 | $0.01122 |
| Sonnet 5 | $0.00011 | $0.00449 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
verify 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 yesterday.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specclaw verify
First, run specclaw-ensure-init .specclaw — idempotently creates .specclaw/ if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name).
Validate that the implementation satisfies the spec.
Step 0 — Validate
specclaw-validate-change .specclaw <change> verify
If it fails (tasks not all complete), report and stop.
If .specclaw/context.md exists, read it before evaluating — the verifier must check that the implementation respects the project's coding rules, patterns, and constraints documented there, in addition to the spec's acceptance criteria.
Step 1 — Collect evidence
specclaw-verify collect .specclaw <change>
Gathers acceptance criteria from spec.md, current contents of changed files, and configured lint/build/test command results — run in that order — followed by the e2e tier when configured.
E2E tier (build.e2e_command + verify.e2e)
build.e2e_command is the slow tier (browser/e2e); build.test_command stays the fast tier. verify.e2e decides when the slow tier runs:
| Policy | Behaviour |
|---|---|
last (default) |
Run e2e only after lint_command, build_command and test_command all pass. An unset fast-tier command is vacuously passing. |
skip |
Never run e2e. |
always |
Run e2e even when an earlier gate failed. |
An absent verify.e2e means last; an unrecognised value warns on stderr and falls back to last.
When the e2e command does run, collect brackets it: it takes a browser slot (specclaw-browser-lock acquire), passes the command through specclaw-browser-lock wrap — which adds --workers=1 for Playwright, one sequential --project= invocation per verify.playwright.projects entry, and a MemoryMax=<verify.playwright.max_memory_mb>M scope when systemd-run is usable — runs the wrapped string, then releases the slot. The slot is released even when the command fails or the run is interrupted. When systemd-run is unusable, wrap warns and the command runs uncapped.
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.
- yesterday Changed · +13 lines 4bbd0987ea8b
- 7d ago First seen · 127 lines · 54 tokens per session scan A ed4aba2d785c
verify is a skill published in the GitHub repository chan4lk/specclaw (12 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 2,243 once invoked, about $0.0003 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
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-foundation-core
Provides MoAI-ADK foundational principles including TRUST 5 quality framework, SPEC-First DDD methodology, delegation patterns, progressive disclosure, agent catalog reference, and token budget management (absorbed from moai-foundation-context). Use when referencing TRUST 5 gates, SPEC workflow, or context window…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…