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 commands/wittyreference/twilio-claude-plugin/knowledge-missgit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00022 | $0.00451 |
| Opus 5 | $0.00011 | $0.00226 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
knowledge-miss 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
Knowledge Miss Logger
Log a knowledge miss event — when Claude should have had context from prior work but didn't.
Input
<user_request> $ARGUMENTS </user_request>
Behavior
-
Classify the miss into one of these categories:
semantic_gap— Content exists in the codebase but keyword search wouldn't find it (e.g., searched for "auth" but answer was in a file about "identity verification")not_in_memory— Content was never captured in memory files or docscross_repo— Content exists in a sibling repo (feature-factory, factory-workshop, twilio-claude-plugin, private-feature-factory)stale— A memory entry exists but is outdated or wrongplan_archaeology— The answer was in a plan file but the plan wasn't discoverable
-
Identify the resolution — briefly note where the information was eventually found (or if it wasn't found at all).
-
Emit the event by running this bash command (substitute the actual values):
source hooks/_emit-event.sh
EMIT_SESSION_ID="${CLAUDE_SESSION_ID:-unknown}"
emit_event "knowledge_miss" "$(jq -nc \
--arg desc 'DESCRIPTION' \
--arg cat 'CATEGORY' \
--arg res 'RESOLUTION' \
'{description: $desc, category: $cat, resolution: $res}')"
- Confirm to the user: "Knowledge miss logged: [category] — [description]"
Query
To review collected data, run:
./scripts/query-events.sh knowledge
Purpose
This data feeds the 90-day RAG adoption decision. If knowledge misses average >2/session with >50% being semantic_gap, the project will adopt vector search. If <1/session, file-based improvements are sufficient.
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 · 52 lines · 22 tokens per session scan A 0dcc2baf9274
knowledge-miss is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 451 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.