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 synaptiai/agent-capability-standard --skill attributegit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWrote 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/synaptiai/agent-capability-standard/attribute)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/attribute"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/attribute/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/synaptiai/agent-capability-standard/attribute"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/attribute.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 | $0.01946 |
| Opus 5.5 | $0.00012 | $0.00778 |
| Sonnet 5.5 | $0.00006 | $0.00389 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
attribute 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 1mo 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Establish causal relationships between observed effects and potential causes. This capability supports root cause analysis, dependency mapping, and causal reasoning for planning and debugging.
Success criteria:
- Causes identified for observed effects
- Causal strength estimated for each relationship
- Causal mechanism explained
- Alternative causes considered and ruled out
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
effect |
Yes | any | The observed effect to attribute |
candidates |
No | array | Potential causes to evaluate |
context |
No | object | Situational context for attribution |
depth |
No | string | Analysis depth: immediate, chain, comprehensive |
Procedure
-
Characterize the effect: Understand what needs to be explained
- Document the observed effect precisely
- Note timing and circumstances
- Identify what changed
-
Identify candidate causes: Generate list of potential causes
- Use provided candidates if available
- Generate additional candidates from context
- Consider proximate and distal causes
-
Evaluate causal strength: Assess each candidate
- Check temporal precedence (cause before effect)
- Verify mechanism plausibility
- Look for correlation evidence
- Consider counterfactual (would effect occur without cause?)
-
Trace causal chain: Map the path from cause to effect
- Identify intermediate steps
- Note amplifying or dampening factors
- Document the causal mechanism
-
Rule out alternatives: Eliminate unlikely causes
- Document why alternatives are less likely
- Note any confounding factors
- Flag when multiple causes may contribute
-
Quantify confidence: Assess attribution certainty
- Rate strength of causal evidence
- Note missing evidence
- Identify what would confirm/refute attribution
Output Contract
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.
- 1mo ago First seen · 262 lines · 29 tokens per session scan A f8338c6fb143
attribute is a skill published in the GitHub repository synaptiai/agent-capability-standard (6 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 1,946 once invoked, about $0.0001 per session on Opus 5.5. 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
deep-code-review
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review.
sodam-harness-self-check
A self-checking instruction set for an AI agent. It tells the agent to verify important work, show evidence, and clearly disclose anything it could not check.
sodam-loop-repair
A Bash safety rule requiring every Bash call to include a timeout calculated from validation settings, with a stated default of 300000 milliseconds. Bash is a command-line shell used to run scripts and commands.
sodam-loop-status
A self-check command for SoDamLoop, a software system with safety components. It checks whether those components are still working normally.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…