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/grcengineering/companion/reflection-journalnpx skills add grcengineering/companion --skill reflection-journalgit clone --depth 1 https://github.com/grcengineering/companionWhat 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 | $0.00055 | $0.00463 |
| Opus 5 | $0.00028 | $0.00231 |
| Sonnet 5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
reflection-journal 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.
What it actually says
reflection-journal
What
Close a learning session by capturing what changed, what remains unclear, and where the learner will apply the idea next.
When
- A session is ending.
- The learner asks for takeaways or reflection.
- A lab, scenario, quiz, or concept session needs closure.
- The learner wants a note they can revisit later.
Not For
- Durable progress state. Use
progress-tracker. - Cold-start or profile updates. Use
profile-wizardorprofile-refresher. - Operational status reporting.
Inputs
- Current session topic and artefact, if any.
- Learner's own stated takeaway.
- Optional progress state.
Steps
Ask:
- What changed in your model?
- What remains unclear?
- Where would this show up in real work?
- What should we revisit next time?
Then produce a concise reflection note and optional progress update proposal.
Validation
- The note distinguishes changed understanding from remaining confusion.
- The next review target is explicit.
- Any real-work application is framed as learning transfer, not advice.
Gotchas
- If the learner wants a compliance status summary, refuse that framing and reflect on learning instead.
- If the learner is tired, ask fewer questions and keep the note short.
- If the reflection reveals profile change, propose it visibly rather than silently updating.
Failure Modes
- Empty summary: require at least one learner-authored takeaway.
- Operational drift: do not summarize programme status.
- Lost next step: always end with a review or practice target.
Examples
- User says "Wrap this up" -> Ask what changed, what is unclear, and what to revisit, then create a short reflection note.
- After a lab -> Capture the artefact, the concept practised, and the next recall checkpoint.
- User says "We are audit-ready now" -> Refuse operational status and reflect on what they learned about audit readiness patterns.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 65 lines · 55 tokens per session scan A 2cf7b2ad59bc
reflection-journal is a skill published in the GitHub repository grcengineering/companion (32 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 463 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 skills, from other repositories
control-mapping
Maps NIST controls to FedRAMP requirements and documents. Use when helping with control implementation, compliance mapping, security baseline alignment, or understanding control requirements.
frmr-analysis
Analyzes FedRAMP FRMR documents to extract control mappings, KSI entries, and version changes. Use when the user asks about FedRAMP requirements, control mappings, compliance data, or needs to understand FRMR document content.
GRC & Compliance
Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.
mapping-builder
Build a reviewed crosswalk (RequirementMappingSet YAML library + review xlsx/csv) between two CISO Assistant framework YAML files using Claude itself as the reasoning engine. Zero infrastructure — stdlib + pyyaml only, no embedders, no LM Studio, no Qdrant. Use when the user asks to map / crosswalk / generate a…
reference-controls-enricher
Enrich a CISO Assistant framework YAML by linking each assessable requirement to reference control URNs from the central doc-pol library (CISO Assistant Key Reference Controls). Produces a reviewable xlsx and patches the framework YAML in place. Use when the user asks to "add reference controls to framework X", "link…
ciso-assistant-basic-risk-assessment
Guide users through a basic risk assessment workflow in CISO Assistant, from asset identification to scenario creation. Use when: (1) User wants to start a risk assessment from scratch (2) User mentions "risk assessment", "identify risks", "threat scenarios", or "risk register" (3) User asks about qualitative vs…