freshness-contract

freshness-contract is a skill for Claude Code from allemaar/open-skills. It costs 203 tokens per session (1,529 once invoked), scanned A, original, Apache-2.0.

A decision table for deciding whether previously collected evidence can still be reused. It considers the type of artifact, its age, changes made since it was collected, and other observable signals.

In plain words
What is it for?
Use it before reusing earlier research, test results, primers, worker reports, or probe findings to decide whether they remain trustworthy or need checking again.
Why use it?
It reduces the risk of relying silently on stale test results, cached documents, reports, or other evidence after relevant conditions have changed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the open-skills plugin — 70 skills shipped together

Good fit Use it before reusing earlier research, test results, primers, worker reports, or probe findings to decide whether they remain trustworthy or need checking again.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/allemaar/open-skills/freshness-contract
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 allemaar/open-skills --skill freshness-contract
Clone the repo
git clone --depth 1 https://github.com/allemaar/open-skills

Made for: Claude Code.

Or install open-skills, the plugin that ships this one along with the rest of its 70 skills.

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 freshness-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/allemaar/open-skills/freshness-contract/github.svg)](https://agentmods.dev/skills/allemaar/open-skills/freshness-contract)
Your own site
<a href="https://agentmods.dev/skills/allemaar/open-skills/freshness-contract"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/freshness-contract/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 freshness-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/allemaar/open-skills/freshness-contract"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/freshness-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,529 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00203 $0.01529
Opus 5 $0.00102 $0.00764
Sonnet 5 $0.00041 $0.00306
Haiku 4.5 $0.00020 $0.00153

Measured 11d ago against content hash 3e447623c203, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

freshness-contract 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/freshness-contract/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/freshness-contract

EXPERIMENTAL. A lookup, not a judgment ritual: it should cost LESS than the vibes it replaces. Fires only when prior evidence is about to be reused for a decision — never on every read, never as per-phase bookkeeping. It decides whether old proof still counts; what fresh proof must show belongs to your verification tools.

The design is deliberately isomorphic to HTTP caching (RFC 9111): explicit invalidation beats heuristics, conflicting signals resolve restrictively, and nothing is served stale silently. No TTL numbers ship in v1 — every "how old is too old" constant would be invented; the table routes by class and events, which are observable.

Step 1 — classify the artifact (volatility class)

Class Meaning Examples
stable exact version-pinned evidence, used for a question about that exact version — byte stability is not applicability: a superseded spec's old bytes still match while the governing version moved a released spec consulted AS that release, a frozen/hash-pinned artifact, an archived record. Supersession or a dependency-version change is a named invalidator whenever the decision asks what is CURRENT
write-coupled valid until someone writes to the source a file you read this session, an index entry, a config, a map/roster document
env-coupled valid until the environment shifts a passing test that touches network/services/installed tools, a capability probe, a build result
clock-coupled decays with time regardless of writes anything embedding "current" state: prices, live statuses, date-dependent results
report someone's account of state, not state itself worker/subagent reports, peer summaries, self-reports of any kind

Class is assigned per artifact kind at first encounter, not re-judged per use by whoever wants to skip a re-read.

Step 2 — check the observable signals

  • Intervening writes — has the source (or its declared dependencies) changed since as_of? (fingerprint, mtime, generation stamp, commit)
  • Named invalidators — did a declared invalidating event occur? (roster change, deploy, sync, schema bump, "re-prime after write")
  • Decision leverage — is the reuse load-bearing for a decision, release, or Handler-facing claim, or merely orientation? Leverage is non-downgradable when the result supports a release, an irreversible or external action, a formal gate, or a Handler-facing recommendation — those are high, not judgment calls.
  • Discriminator availability — does a cheap signal exist that is exclusive to the fresh state (a hash to recompute, a header to stat, a count to re-derive)?

Read the full file on GitHub · 79 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 · 79 lines · 203 tokens per session scan A 3e447623c203

Subscribe to this mod's changes

freshness-contract is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed today), licensed Apache-2.0. It adds 203 tokens to every session and 1,529 once invoked, about $0.0010 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.