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 bdfinst/agentic-dev-team --skill feedback-learninggit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/bdfinst/agentic-dev-team/feedback-learning)<a href="https://agentmods.dev/skills/bdfinst/agentic-dev-team/feedback-learning"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/feedback-learning/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/bdfinst/agentic-dev-team/feedback-learning"><img src="https://agentmods.dev/badge/skills/bdfinst/agentic-dev-team/feedback-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.04765 |
| Opus 5.5 | $0.00021 | $0.01906 |
| Sonnet 5.5 | $0.00011 | $0.00953 |
| Haiku 4.5 | $0.00005 | $0.00477 |
Grade A, and why
feedback-learning 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 — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feedback & Learning
Procedure for capturing user feedback, updating configurations dynamically, and maintaining an audit trail of all changes.
Trigger Keywords
| Keyword | Intent | Example |
|---|---|---|
| amend | Modify existing behavior | amend: the software engineer should prefer functional patterns |
| learn | Teach something new | learn: our API uses kebab-case URLs |
| remember | Persist a preference across sessions | remember: always run tests before completing tasks |
| forget | Remove a previous preference | forget: the kebab-case URL convention |
All four follow the same processing flow. The distinction is semantic (helping the user express intent), not mechanical.
Where Changes Are Written
The plugin ships as a read-only cache — agent and skill files inside the plugin cannot be edited. Instead, feedback is persisted to project-local files that the user controls and that Claude Code loads automatically.
Resolution order
When processing a feedback keyword, determine the right destination:
| Change type | Write to | Why |
|---|---|---|
| Project convention or preference | Project CLAUDE.md (.claude/CLAUDE.md or repo-root CLAUDE.md) |
Loaded every session, applies to all agents |
| Review context (domain knowledge, known issues, team norms) | REVIEW-CONTEXT.md in project root |
Read by /code-review and passed to every review agent |
| Agent behavior override for this project | Project CLAUDE.md under a ## Agent Overrides section |
Overrides plugin defaults without editing plugin files |
| Cross-session memory (decisions, project state) | .claude/memory/ files |
Persists across context resets |
| Rollback a previous change | Reverse the edit in whichever file it was written to | Logged as type: "rollback" |
What NOT to do
- Do not edit files inside the plugin cache (
~/.claude/plugins/cache/...). Changes there are overwritten on plugin updates. - Do not create new agent or skill files in the project. Instead, add override instructions to project
CLAUDE.md.
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 · 415 lines · 53 tokens per session scan A a84b01296893
feedback-learning is a skill published in the GitHub repository bdfinst/agentic-dev-team (295 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 4,765 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
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…