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.
git clone --depth 1 https://github.com/kristijankopacevic/optiflow-mcpWrote 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/commands/kristijankopacevic/optiflow-mcp/report)<a href="https://agentmods.dev/commands/kristijankopacevic/optiflow-mcp/report"><img src="https://agentmods.dev/badge/commands/kristijankopacevic/optiflow-mcp/report/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kristijankopacevic/optiflow-mcp/report"><img src="https://agentmods.dev/badge/commands/kristijankopacevic/optiflow-mcp/report.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00469 |
| Opus 5 | $0.00018 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
report 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 8d 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
Run optiflow's transcript analytics report and show the result to the user.
This parses Claude Code's own local transcript files
(~/.claude/projects/<slug>/<sessionId>.jsonl) directly — a disjoint data
source from token-optimizer-mcp's analytics DB, which only records what its
own smart_* tools saved. This report is about prompt/cache economics for
the actual conversation(s): total tokens per session, where the prompt
cache broke (had to be re-primed instead of reused), subagent/Task-tool
token usage separated from the main thread, and which turns cost the most.
Run:
optiflow report $ARGUMENTS
If no arguments are given, this defaults to the current project's
transcripts (best-effort — derived from the directory Claude Code was
launched from) in table format over all history. Useful variations:
optiflow report --session <id>— analyze one specific session by id, regardless of which project it's filed under (the most reliable lookup — seesrc/transcript/discover.tsfor why current-project discovery is best-effort).optiflow report --all --format markdown— analyze every local project's transcripts and produce a table suitable for pasting into a PR/doc.optiflow report --range 7d— only include turns from the last 7 days.optiflow report --format json— machine-readable output.
If the command reports "no transcript files found," suggest --session <id> or --all rather than assuming something is broken — this is a
normal outcome when the CLI's current working directory doesn't match the
directory Claude Code was originally launched from (see the tool's own
--help and docs/modules.md for the exact caveat).
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.
- 8d ago First seen · 36 lines · 36 tokens per session scan A 0ea9cb76f2e3
report is a command published in the GitHub repository kristijankopacevic/optiflow-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 469 once invoked, about $0.0002 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.