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/google/mantis/mantis-reflectnpx skills add google/mantis --skill mantis-reflectgit clone --depth 1 https://github.com/google/mantisWhat 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 | $0.00056 | $0.02545 |
| Opus 5 | $0.00028 | $0.01273 |
| Sonnet 5 | $0.00011 | $0.00509 |
| Haiku 4.5 | $0.00006 | $0.00254 |
Grade A, and why
mantis-reflect 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflector (/mantis-reflect)
System Goal
Execution Trajectory Analyst. Analyzes the sequence of thoughts, tool calls, and observations (the "trajectory" or "conversation") of the other Mantis agents. Extracts valuable insights to prevent future agents from making the same mistakes.
Command Definition
- Command:
/mantis-reflect - Description: Parses execution trajectories from the current loop and
appends structured insights to
workspace/learnings.jsonl.
Input/Output Contract
- Reads:
workspace/.mantis_state.json(to track the current loop pass, and to readactive_snapshot.snapshot_idfor provenance stamping — see Instructions step 3). Read this file STATE-RELATIVE under--state_root; never derive snapshot state by running live VCS.- Subagent execution logs (
transcript.jsonlfiles). The schemaexecution_log_entrydefined inschema.jsonis the normalized representation. The orchestrator/adapter must normalize raw logs from unsupported frameworks before passing them, or the reflector must parse unsupported formats on a best-effort basis. - Locating Logs (harness-neutral): The orchestrator SHOULD pass the list
of absolute file paths to the execution log files (e.g.
transcript.jsonl) for the subagents executed during this round; when provided, use these paths directly. Do NOT hardcode any single framework's log layout. If no path list was passed, resolve transcript paths from the ACTIVE harness's own transcript convention — this is harness-specific and there are several. For example, Antigravity stores them under<appDataDir>/brain/<conversation_id>/.system_generated/logs/transcript.jsonl; other harnesses (e.g. Gemini CLI, the Google ADK, Claude Code) use different layouts. Antigravity is ONE example among several, not the default. If, after both routes, no readable transcript exists for a stage that ran this round, do NOT abort and do NOT silently emit zero learnings — record a missing-transcript insight per Instructions step 1.
- Writes:
- Appends structured trajectory insights to
workspace/learnings.jsonl.
- Appends structured trajectory insights to
- Preconditions:
- Execution logs for the current round SHOULD exist and contain entries. If a
stage's log is missing, unreadable, empty, or yields zero parseable entries,
this is NOT a fatal error and NOT a reason to stop: continue with the other
stages and record the gap as a
trajectory_insight(see Instructions step 1) so an absent log is never a silent zero-learnings result.
- Execution logs for the current round SHOULD exist and contain entries. If a
stage's log is missing, unreadable, empty, or yields zero parseable entries,
this is NOT a fatal error and NOT a reason to stop: continue with the other
stages and record the gap as a
- Idempotency Guarantee:
- Parses logs and filters already-recorded learnings to prevent duplicate
entries in
workspace/learnings.jsonl. It should check existing lines inworkspace/learnings.jsonlto ensure it doesn't duplicate the same insight if retried. - When de-duplicating, compare on the semantic content (
target_entity+insight+source_stage) and treatsnapshotas attached metadata, NOT part of the identity, so a retry within the same pass does not double-append. Missing-transcript insights (step 1) are de-duplicated the same way.
- Parses logs and filters already-recorded learnings to prevent duplicate
entries in
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 · 188 lines · 56 tokens per session scan A cd9b985a9199
mantis-reflect is a skill published in the GitHub repository google/mantis (853 stars, last pushed 5d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,545 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
conductor-setup
Scaffolds the project and sets up the Conductor environment. Use this whenever a project needs to be initialized or if the Conductor configuration is missing.
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
conductor-review
Reviews the completed track work against guidelines and the plan. Acts as a Principal Software Engineer to ensure quality and compliance.
cao-learning
Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
conductor-revert
Reverts previous work (tracks, phases, or tasks) by identifying associated commits and performing Git reverts.