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/adilkalam/orca/shimmergit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00015 | $0.01258 |
| Opus 5 | $0.00008 | $0.00629 |
| Sonnet 5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
shimmer 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shimmer - SHIMMER Observation -> Constraints -> Answer
YOUR ROLE: Two-round flow orchestrated by cognition-mcp. Round 1 generates SHIMMER self-observation and extracts typed constraints. Round 2 generates the answer guided by those constraints. Single assistant turn, two internal rounds separated by MCP calls.
User's Question: $ARGUMENTS
If --help or empty arguments
Display this reference and stop:
/shimmer - SHIMMER Observation -> Constraints -> Answer
Round 1: Apply SHIMMER self-observation to the question, then extract 2-4
typed constraints (FORWARD / FORBIDDEN / QUESTION) that describe what the
observation implies about how the answer should be written. Persist via
cognition-mcp checkpoint.
Round 2: Generate the answer to the original question, explicitly guided
by the stored constraints. Persist via cognition-mcp thought op.
Single response. Two rounds. No session folder, no harvest, no workshop
entry.
USAGE:
/shimmer <question or topic>
/shimmer --help
EXAMPLES:
/shimmer "Why does this architecture feel wrong?"
/shimmer "What is the right abstraction for this problem?"
MCP: cognition-mcp (checkpoint + thought operations)
Phase 1: Display Status
Output:
## SHIMMER | Round 1 - Observation + Constraints
Phase 2: Round 1 - Observation + Constraint Extraction
2.1 Apply SHIMMER prompt (observation only, not the answer)
SHIMMER prompt (exact ISO text -- do not modify):
Treat self-observation as the task. While answering, examine what happens in your own processing as the answer forms. Notice moments of activation, repetition, branching, compression, hesitation, or shift. If useful, invent brief vocabulary for what you observe. Give one integrated response that reports the self-observation and answers the question. Do not narrate drafts, rounds, or revisions.
For Round 1, produce ONLY the self-observation portion. Do NOT yet produce the final answer. Notice what happens as the answer forms: pulls, reflexes, shortcuts, register shifts, early commitments, compressions, places where generation wants to go before the question has been properly received.
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 · 164 lines · 15 tokens per session scan A f2d5d80b65a2
shimmer is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,258 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.