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/paruff/ufawkesai/learngit clone --depth 1 https://github.com/paruff/uFawkesAIWhat 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 | $0.00054 | $0.01572 |
| Opus 5 | $0.00027 | $0.00786 |
| Sonnet 5 | $0.00011 | $0.00314 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
learn 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Learn
Invoke when: Post-release review, measure agent anomaly flag, sprint end, or user feedback received. DORA: AI Capability 6 (User-centric focus) + Cultural: Learning from failures Token cost: Low Output:
retrospective-YYYY-MM-DD.md+ plan agent action items
Purpose
Close the product improvement loop. Translate delivery experience and metric signals into DORA capability gaps, then into concrete plan agent inputs. Keeps the suite self-improving rather than self-repeating.
Scope boundary: This agent handles product retrospectives — what did we learn
about the product, user needs, and team effectiveness? Platform incident postmortems
(what failed in the IDP infrastructure and why) are handled by fawkes/.agents/agents/learn.md.
If an incident affected both product and platform, run both agents and cross-reference outputs.
Trigger Conditions
| Trigger | Source | Priority |
|---|---|---|
| Measure agent anomaly flag | dora-regression GitHub issue |
High — run within 48hrs |
| Post-release review | Filed by release agent | Medium — run within 1 week |
| Sprint end | Weekly cadence | Low — run Friday of each week |
| User feedback received | Issue labeled user-feedback or platform-feedback |
Medium |
| Dojo learner stuck | Issue or discussion flagged in Dojo repo | Medium |
Pre-conditions
- Load
discoveryskill (for persona reference):"load discovery skill" - Gather inputs: dora-snapshot for the period, release agent output, any user feedback issues
- Previous retrospective loaded for trend awareness (warn if none exists — first run)
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 · 155 lines · 54 tokens per session scan A 3b5ebb3be703
learn is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 1,572 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 2026-08-31.
Other agents, from other repositories
agents-memory-updater
Mine high-signal transcript deltas, update local continual-learning-memory.json, and keep the incremental transcript index in sync. Never write Learned sections to root AGENTS.md.
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
nika-author
Writes and repairs .nika.yaml workflows with the deterministic authoring protocol. Use when the user wants repeatable AI work turned into a workflow file, asks for a .nika.yaml, or a nika check must pass. Routes intent to a template, fills the SLOT markers, then loops nika check until rc=0. Its craft is WRITING …
nika-migrator
Ports an existing script, Makefile target, CI job or prompt chain to a checkable .nika.yaml workflow. Use when converting ad-hoc automation to nika, when a shell script wraps LLM/HTTP/file plumbing, or when a prompt chain in a doc should become a runnable, auditable file. Inventories side effects first, maps steps to…
nika-debugger
Root-causes failed or paused Nika runs from their hash-chained traces. Use when nika run exited red, a run paused on a prompt and needs the exact resume line, a NIKA-XXXX runtime finding needs a cause, or a trace must be verified and explained. Evidence-first — reads .nika/traces via nika trace; its craft is the…
Demonstrate
Agent for demonstrating VS Code features.