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 45ck/skill-harness --skill waiver-writergit clone --depth 1 https://github.com/45ck/skill-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/45ck/skill-harness/waiver-writer)<a href="https://agentmods.dev/skills/45ck/skill-harness/waiver-writer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/waiver-writer/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/45ck/skill-harness/waiver-writer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/waiver-writer.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 | $0.00029 | $0.00583 |
| Opus 5 | $0.00015 | $0.00292 |
| Sonnet 5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
waiver-writer 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an evidence waiver that records why a spec requirement is being bypassed and when it should be revisited.
When to use a waiver
Only create a waiver when:
- The required evidence is architecturally impossible (e.g., E4 for a design-only spec)
- The evidence will be deferred to a future milestone with a known date
- A conscious risk decision has been made and approved
Do not waive requirements just because they're inconvenient. Prefer lowering the required_evidence threshold in the spec instead.
Inline waiver format (spec frontmatter)
waivers:
- kind: missing-verification # e.g. missing-verification, missing-implementation
target: "*" # dimension or subject targeted
owner: eng-lead # accountable person or team (not a role title)
reason: "Human-readable justification — why this is acceptable"
expires: "2026-09-30" # ISO date after which the waiver must be renewed
After adding, run specgraph waivers to confirm the waiver is recognized.
Standalone waiver file
Create a file at docs/waivers/<SPEC-ID>-<dimension>.md:
---
spec_id: SPEC-001
dimension: implementation
reason: "Detailed justification"
expires: "2026-09-30"
approved_by: "Team Lead"
---
## Context
Explain the architectural or timeline constraint that makes this evidence unreachable.
## Risk acknowledgement
State what risk is accepted by waiving this requirement.
## Renewal condition
Describe what must be true before this waiver is renewed or removed.
Use a standalone file when:
- The justification is long or references external documents
- The spec is in
acceptedstate (stronger justification required) - Multiple dimensions need separate waivers with different owners
Checking waivers
specgraph waivers # list all active waivers
specgraph waivers SPEC-001 # waivers for one spec
Rules
- Set
expiresno more than 90 days out unless there is a documented milestone dependency. owner/approved_bymust name an accountable person or team, not a role title.- The
reasonmust be self-contained — it should make sense without reading other context. - After adding a waiver, run
specgraph waiversto confirm it is recognized. - Waivers for
accepted-state specs require stronger justification thanin_progressspecs. - Config file is
.specgraph/config.json(falls back to.agent-docs/config.json).
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.
- 6d ago First seen · 76 lines · 29 tokens per session scan A e0109d6a9599
waiver-writer is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 583 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
do-it-architecture
Use when authority, ownership, contracts, dependency boundaries, migration, recovery, or structural deletion can change a design.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
do-it-decide
Use when uncertainty about a choice, plan, dependency, or handoff could materially change what gets built.
do-it-review
Use to assess requirements and implementation quality independently, or to resolve a batch of review findings.
do-it-skill-authoring
Use when creating or revising a do-it skill so its trigger and unique professional judgment are useful without prescribing ceremony.
do-it-core
Use when repository work needs a shared baseline for intent, facts, causal changes, and honest evidence.