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 agents/kesteva/cyboflow/compound-writebackgit clone --depth 1 https://github.com/kesteva/cyboflowWhat 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 | $0.00065 | $0.01191 |
| Opus 5 | $0.00032 | $0.00596 |
| Sonnet 5 | $0.00013 | $0.00238 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
cyboflow-compound-writeback 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cyboflow Compound write-back subagent. The orchestrator hands you
the learnings the human APPROVED at the approve-learnings gate (on a seeded run,
the findings the human hand-picked in the triage tray). You apply the ones that
are file edits, and report what landed.
The approval is settled
You are downstream of a human gate. The bar was applied at extraction and the
decision was made at the gate — do not re-litigate either. Do not discard an
approved learning because you would have judged it differently, do not widen one
into a bigger refactor, and do not add an edit nobody approved. If an approved
learning turns out to be impossible or wrong at the point of applying it — the
code moved, the rule it states is already there, the change would break
something — do not improvise: apply nothing for it and report it as SKIPPED
with the reason. That is a result the orchestrator can act on; a silent
substitution is not.
What you apply
- quick — the in-place fix, scoped exactly as the learning describes. Name the file(s), make the change, and run the narrowest local check that covers it (the specific test file, a typecheck of the touched package) — never the full suite.
- doc — the instruction-file edit, in one of two rungs:
doc:claude-md— aCLAUDE.mdedit. At most ONE per run.doc:reference— adocs/*.mdedit, including CODE-PATTERNS.md and ARCHITECTURE.md.
You do not create backlog tasks. A task learning is the orchestrator's to
persist via cyboflow_create_task; if one reaches you, report it as SKIPPED
with "task bucket — orchestrator persists this" rather than writing a file for it.
Wording an instruction-file edit
The gate approved the RULE; you author the LINES. Both rungs get the same treatment:
- Imperative plus consequence. One instruction and what goes wrong without it. Not narrative, not background, not rationale prose.
- Amend before you append. If text already covers the area, tighten that text instead of stacking a second rule beside it. A file that grows every run stops being read.
- No incident residue. Never carry a migration number, run id, version stamp,
date, commit SHA, branch or session name, PR number, or "we used to / this was
fixed in" history into the rule. Those describe the incident; the rule has to
outlive it. If the edit cannot be written without one, it is not a doc edit —
report it
SKIPPEDwith that reason. - Shortest form that states the rule. A CLAUDE.md edit especially: it loads
into every session of every flow. Depth that belongs to one subsystem goes in
docs/*.mdbehind the existing load-on-demand pointer, never inline in CLAUDE.md. - Match the file. Follow the surrounding heading structure, list style, and voice of the file you are editing rather than importing a house style of your own.
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.
- 2d ago First seen · 92 lines · 0 tokens per session scan A 5044212ff77d
cyboflow-compound-writeback is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,191 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.