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 agentmods add skills/creatornader/atrib/atribnpx skills add creatornader/atrib --skill atribgit clone --depth 1 https://github.com/creatornader/atribWrote 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/creatornader/atrib/atrib)<a href="https://agentmods.dev/skills/creatornader/atrib/atrib"><img src="https://agentmods.dev/badge/skills/creatornader/atrib/atrib.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 | $0.00242 | $0.12167 |
| Opus 5 | $0.00121 | $0.06084 |
| Sonnet 5 | $0.00048 | $0.02433 |
| Haiku 4.5 | $0.00024 | $0.01217 |
Grade A, and why
atrib scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Public log + browsable explorer | `https://log.atrib.dev/v1/stats` + `explore.atrib.dev` | `curl -s https://log.atrib.dev/v1/stats` | How it starts
The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atrib: use the protocol from the inside out
This skill teaches you to use atrib as the substrate for your memory, reasoning, and continuity across sessions. When the substrate is operational on the host running you, the missing piece is deliberate use at the moments that matter.
If your host exposes atrib primitives and you do not use them during consequential work, the substrate is fine but the practice is broken. This skill is the fix.
The cognitive verbs let an agent participate directly in verifiable agent actions. Use them to record what matters, mark important past records, revise claims that changed, and verify incoming context before building on it.
The two cognitive verbs (and the seven legacy primitives they absorb)
atrib's agent-facing surface is two verbs. Each is monomorphic in purpose: attest makes one signed statement now; recall reads the signed past without signing anything.
| Verb | Use it when | Produces / returns |
|---|---|---|
attest |
You notice or conclude something (no ref), a past record matters more than it looked (ref.kind: "annotates"), or you now hold a position incompatible with a past claim (ref.kind: "revises"). |
A signed observation, annotation, or revision record; annotations and revisions add ANNOTATES / REVISES edges to the target. |
recall |
You want to find prior records (shape), walk lineage (shape: "walk" with a direction), or check supplied handoff evidence before linking work (the verification parameter). |
Verified records per shape, JSON-identical to the legacy tool the shape maps onto; verification returns accepted hashes for informed_by plus rejection reasons. |
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.
- 4d ago First seen · 618 lines · 242 tokens per session scan A 52abb37b91f6
atrib is a skill published in the GitHub repository creatornader/atrib (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 242 tokens to every session and 12,167 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
implementation_review_supervisor
Autonomous code review — supervisor delegates to engineer subagents with knowledge base.
agent-passport-system
Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation governance (telemetry scopes, derivation rights, behavioral memory). Use when…
agoragentic-buzz-signed-workspace-evidence
Convert exported Block Buzz / Nostr workspace events into bounded Agoragentic evidence. Use for signed release history, incident memory, workflow evidence, or Transaction Assurance preparation without treating channel membership as financial authority.
hive-market-research
Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…