Mission Replan Loop

What it does

When your agent uses it

• A call may invalidate the plan rather than simply complete a step

Example prompts

• “/mission-replan-loop”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

1. 1Read the mission objective, deadline and constraints.
2. 2Read the current strategy and its target.
3. 3Normalise the CALL-E result into structured evidence.
4. 4Preserve provenance: every fact keeps its call_id, target and timestamp.
5. 5Evaluate the evidence against the constraints — deterministically.
6. 6Return VALID, INVALID, UNCERTAIN or INFEASIBLE.
7. 7INVALID → propose a replacement strategy that materially differs from the failed one.
8. 8UNCERTAIN → propose a clarification, never a decision.
9. 9Generate the next operation needed to validate the new strategy.
10. 10Apply host policy before anything executes.
11. 11INFEASIBLE → escalate. Escalation is a valid result.

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mission Replan Loop loads about 1.6k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 751 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~68

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 751 words, ~1,599 tokens.

name

mission-replan-loop

description

Turn CALL-E phone results into structured mission evidence, evaluate whether the current strategy is still viable, and generate the next operation when reality changes the plan. Use when a call may invalidate the plan rather than simply complete a step.

CALL → EVIDENCE → CONSTRAINT → STRATEGY STATUS → CONTINUE / REPLAN → NEXT CALL

mission:     { objective, deadline }
constraints: [ { key, operator, value, mandatory } ]
strategy:    { id, type, target }
call_result: { call_id, target, status, facts: { ... } }
policy:      { allowed, approval_required, prohibited }

evidence:          [ { fact, value, source_call, confidence, status } ]
constraint_results: [ { constraint, required, observed, status } ]
strategy_status:   valid | invalid | uncertain | infeasible
replan:            { required, reason, previous_target, proposed_strategy }
next_operation:    { type, objective, required_information }
policy_result:     { status }
escalation:        { required, reason }

© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/mission-replan-loop of CALLE-AI/awesome-phone-call-agents.

• SKILL.md
• examples/field-service-recovery.yaml
• examples/logistics-recovery.yaml
• examples/procurement-recovery.yaml
• examples/uncertain-answer.yaml
• examples/unsupported-destination.yaml
• references/examples.md
• references/mission-state.md
• references/replanning-policy.md
• references/safety.md
• schemas/mission.schema.json
• schemas/result.schema.json

Open the folder on GitHubat commit 38d4118