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/dcassil/resume-kit/learn-changenpx skills add dcassil/resume-kit --skill learn-changegit clone --depth 1 https://github.com/dcassil/resume-kitWrote 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/dcassil/resume-kit/learn-change)<a href="https://agentmods.dev/skills/dcassil/resume-kit/learn-change"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/learn-change.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 | $0.00066 | $0.01059 |
| Opus 5 | $0.00033 | $0.00530 |
| Sonnet 5 | $0.00013 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
learn-change 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 3d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renamed:
learn-changewaslog-edit-feedbackbefore v1.0.0 (see RIT-A-0005).
learn-change - record outcome -> preference pair -> refresh preferences
Purpose
Preference learning improves only when outcomes are recorded. This skill writes
one EditFeedback record for one real edit suggestion the user saw, optionally
writes the PreferencePair implied by that outcome, then refreshes
resume-kit/learning/preferences.json.
Use this for outcomes from rank-changes recommendations or edit-session
decisions from update-keywords / update-terminology. Do not log
speculative edits the user never saw.
Prerequisites Gate
Run the shared prerequisites gate in
../_shared/prerequisites.md, then confirm:
- There is one in-flight suggestion or committed edit decision.
- The user outcome is known:
accepted,accepted_modified,rejected, orundone. - You have the fields needed for
EditFeedback: edit id, resume id, job id, section, edit type, original text, proposed text, final text when kept, target terms, matched job requirements, predicted ATS gain, confidence, and timestamp.
If there is no real suggestion and no user outcome, stop. Route the user to rank-changes or the edit-session loop first.
Reason Codes
For accepted_modified, rejected, and undone, offer the
EditFeedbackReasonCode enum:
fabrication, overclaim, unsupported, grammar, formatting,
not_my_voice, too_verbose, too_vague, wrong_emphasis, duplicate,
other.
Store the selected enum as reason_code. A short optional note is allowed as
reason_note; do not use legacy free-text-only rejection reasons for new
records.
Surfaces This Skill Drives
- CLI:
resume-tool record-edit-feedback --feedback <feedback.json> [--preference-pair <pair.json>] [--base-path <resume-kit>] - MCP tool:
edit_feedback_record - Facade capability:
record-edit-feedback - Preference refresh CLI:
resume-tool refresh-preferences --now <iso> [--records <records.json>] [--base-path <resume-kit>] - Preference refresh MCP tool:
preferences_refresh - Preference refresh facade capability:
refresh-preferences
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.
- 3d ago First seen · 102 lines · 66 tokens per session scan A 01780e6ffe4b
learn-change is a skill published in the GitHub repository dcassil/resume-kit (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,059 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 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…