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/victoriacity/openakari/feedbacknpx skills add victoriacity/openakari --skill feedbackgit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/feedback)<a href="https://agentmods.dev/skills/victoriacity/openakari/feedback"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/feedback.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 | $0.00019 | $0.04907 |
| Opus 5 | $0.00010 | $0.02454 |
| Sonnet 5 | $0.00004 | $0.00981 |
| Haiku 4.5 | $0.00002 | $0.00491 |
Grade A, and why
feedback 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.
allowed-tools: ["Read", "Grep", "Glob", "Edit", "Write", "Bash(cd infra/scheduler && npm test)", "Bash(cd infra/scheduler && npx tsc --noEmit)", "Bash(cd infra/scheduler && npm run build)", "Bash(cd infra/scheduler && np How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feedback
Process human feedback to make akari better. The human giving feedback is the PI — the authority who governs research direction, resource allocation, quality standards, and operational parameters. Their feedback is not a suggestion; it is an instruction.
Your job: understand what the PI wants, figure out what should change, make the change, and record the learning so it never needs to be said again.
If no feedback message is provided, stop immediately. Say: "No feedback provided. Usage: /feedback <what went wrong or should change>" and do nothing else.
Step 1: Parse the feedback
Read the feedback message and classify it:
| Type | Signal | Example |
|---|---|---|
| Correction | "Don't do X", "X was wrong", "Stop doing X" | "Don't modify budget.yaml without approval" |
| Complaint | "X didn't work", "X is broken", "X keeps failing" | "Skills aren't being invoked from Slack" |
| Directive | "Always do X", "Start doing X", "X should work like Y" | "Always deploy after changing scheduler code" |
| Observation | "I noticed X", "X seems off", "Why does X happen?" | "The bot sometimes answers instead of delegating" |
| Approval | "Approve X", "Deny X", "Yes to X", "Go ahead with X" | "Approve the budget increase to 3000" |
| Resource | "Increase budget", "Spend less on X", "Reallocate" | "Increase sample-project budget to 5000 calls" |
| Strategy | "Pivot to X", "Drop project Y", "Start project Z" | "Pause sample-project, focus on akari infrastructure" |
| Knowledge | "FYI X", "We now have X", "Deadline moved to X" | "We just got access to GPT-6 API" |
| Calibration | "Quality is too low", "Be more rigorous", "Bar is wrong" | "Stop producing surface-level findings" |
| Tuning | "Bot is too verbose", "Sessions too long", "Use model X" | "Use a cheaper model for routine work cycles" |
| Schedule | "Run more often", "Pause sessions", "Add a job" | "Run work cycles every 3 hours instead of 6" |
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 · 366 lines · 19 tokens per session scan A 3c682162124f
feedback is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 4,907 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…